Precision agronomy in semi-arid regions: Role of GIS, remote sensing and AI in crop management

Introduction

Semi-arid regions cover approximately 40% of the global land surface and are characterized by low and irregular rainfall distribution, high evapotranspiration demand, and inherently low soil fertility that restrict agricultural productivity (UNEP, 2021) [25] . Agricultural systems in these regions are highly vulnerable to climate variability, drought frequency, and limited natural resources, which significantly affect crop growth and yield stability (Dai, 2018) [17] . Water scarcity, declining soil health, and inefficient nutrient management further intensify production risks in semi-arid agroecosystems (Foley et al., 2019) [18] . Therefore, innovative and resource-efficient crop management strategies are essential to sustain agricultural productivity under these challenging environmental conditions (Tilman et al., 2017) [23] . Precision agronomy has emerged as an advanced scientific approach that utilizes modern digital tools to manage spatial and temporal variability within agricultural fields (McBratney et al., 2018) [22] . Precision agriculture involves systematic collection, processing, and analysis of field-level variability data to support informed decision-making regarding irrigation scheduling, nutrient application, pest control, and crop productivity improvement (Bramley, 2019) [15] . The concept focuses on applying the right input, at the right time, and at the right place, thereby improving resource-use efficiency and minimizing environmental degradation (Gebbers et al., 2020) [19] . Geographic Information System (GIS) technology helps in mapping soil characteristics, crop variability, and land suitability patterns using spatial databases and geostatistical tools (Tomlinson, 2017) [24] . Remote sensing technologies provide continuous monitoring of crop growth, canopy reflectance, vegetation indices, soil moisture status, and stress conditions using satellite and aerial platforms (Xue & Su, 2017) [26] . Artificial Intelligence (AI) techniques such as machine learning and data analytics process large volumes of agricultural data to generate predictive models that improve farm-level decision-making accuracy (Chlingaryan et al., 2018) [16] . Integration of GIS, remote sensing, and AI-based technologies helps farmers optimize input use, reduce production costs, improve crop yield, and enhance sustainability in moisture-limited semi-arid farming systems (Balafoutis et al., 2017) [14] . Digital agriculture tools support climate-resilient crop management by improving water-use efficiency, nutrient-use efficiency, and early detection of crop stress conditions (Khanal et al., 2020) [20] . Adoption of precision agronomy practices contributes to sustainable intensification and long-term productivity of semi-arid agricultural systems (Lowenberg-DeBoer et al., 2019) [126,21] .

Characteristics of Semi-arid Agriculture

Semi-arid agroecosystems are characterized by multiple biophysical and climatic constraints that limit crop productivity and threaten long-term sustainability of agricultural systems (Reynolds et al., 2017) [38] . These regions typically receive low and erratic rainfall, resulting in frequent dry spells and uneven soil moisture distribution that adversely affects crop growth and development (Nicholson, 2018) [36] . High temperature stress and intense solar radiation increase evapotranspiration demand, leading to rapid depletion of soil moisture and increased risk of drought stress during critical crop growth stages (Hatfield & Prueger, 2019) [32] . Low soil organic matter content is a common problem in semi-arid soils, which reduces waterholding capacity, soil structure stability, and nutrient availability to plants (Minasny & McBratney, 2018) [35,22] . Nutrient deficiencies, particularly nitrogen, phosphorus, and micronutrients, further limit crop productivity due to poor soil fertility and low biological activity (Fixen et al., 2019) [31] . Water scarcity remains one of the major limiting factors in semi-arid agriculture, affecting irrigation availability and reducing crop yield potential (Falkenmark, 2017) [30] . Land degradation processes such as soil erosion, salinization, and desertification also threaten the sustainability of crop production systems in these fragile environments (D'Odorico et al., 2018) [29] .

Major crops cultivated in semi-arid regions include maize, sorghum, pearl millet, groundnut, chickpea, sunflower, and cotton, as these crops possess adaptive traits such as drought tolerance and efficient water-use mechanisms (ICRISAT, 2019) [33] . Efficient management of water resources, soil fertility, and crop health is essential to maintain productivity and ensure stability of farming systems under limited moisture conditions (Passioura, 2017) [37] . Sustainable agronomic practices such as conservation tillage, integrated nutrient management, and crop diversification improve resilience of semi-arid farming systems (Lal et al., 2018) [34] . Precision agronomy tools help identify spatial variability in soil moisture status, nutrient availability, and crop vigor using advanced sensing and mapping technologies (Adamchuk et al., 2018) [27] . Site-specific crop management enabled by precision agriculture improves input-use efficiency, reduces environmental losses, and enhances productivity in semi-arid agroecosystems (Corwin & Lesch, 2019) [74,28] . Adoption of spatial decision-support tools supports better management of soil and water resources under climate variability conditions (Zhang & Kovacs, 2018) [123,39] .

Role of Gis in Precision Agronomy

Geographic Information System (GIS) is a computer-based technology used to capture, store, manage, analyze, and visualize spatial and temporal data related to agricultural resources (Longley et al., 2019) [46] . GIS plays an important role in precision agronomy by enabling spatial mapping of soil properties, crop growth variability, and yield distribution patterns across agricultural fields (Mulla, 2018) [49] . Spatial analysis using GIS helps researchers and farmers understand field heterogeneity and supports site-specific crop management decisions for improving productivity and resource-use efficiency (Robert, 2017) [50] . GIS-based mapping techniques provide valuable insights into soil nutrient variability, soil texture distribution, and land capability classification for sustainable crop production (Heuvelink & Webster, 2019) [44] .

Applications of GIS in Semi-Arid Regions

GIS technology is widely used for soil fertility mapping, which helps identify spatial variability of essential nutrients and supports precise fertilizer application (Hartemink, 2018) [43] . Land suitability analysis using GIS assists in selecting appropriate crops based on soil characteristics, climatic conditions, and topographical features (Malczewski, 2017) [47] . Crop zoning helps classify agricultural land into different productivity zones for effective crop planning and management (FAO, 2022) [42] . Nutrient variability mapping enables efficient nutrient management by identifying deficient and surplus zones within the field (McBratney et al., 2017) [48] . Drought risk assessment using GIS tools helps evaluate spatial patterns of rainfall variability and soil moisture stress in semi-arid environments (Vicente-Serrano et al., 2019) [52] . Yield variability analysis supports identification of high-and low-yielding zones, allowing farmers to optimize input use and maximize productivity (Basso et al., 2019) [40] .

GIS enables integration of multiple spatial data layers such as soil type, rainfall distribution, slope gradient, elevation, and crop productivity to support better farm planning and resource allocation decisions (Tomlinson et al., 2018) [51] . Spatial decision-making supported by GIS improves crop selection strategies and enhances efficiency of input management practices under variable environmental conditions (Eastman, 2017) [41] . GIS-based decision support systems help optimize fertilizer recommendations and irrigation scheduling by integrating soil, weather, and crop information under limited water availability conditions (Jones et al., 2017) [45] .

Role of Remote Sensing in Precision Agronomy

Remote sensing is a non-destructive technology that enables acquisition of crop and soil information using satellite platforms, unmanned aerial vehicles (UAVs), and groundbased sensors without physical contact with the field (Campbell & Wynne, 2017) [57] . It provides large-scale and real-time observations of agricultural systems, supporting efficient monitoring of crop growth conditions and environmental variability (Pettorelli et al., 2018) [62] . Multispectral and hyperspectral imaging techniques capture reflectance patterns from plant canopies, enabling detailed assessment of plant health, chlorophyll content, and stress symptoms under varying environmental conditions (Blackburn, 2018) [55] . These technologies provide valuable information about soil moisture dynamics, crop vigor, and nutrient status across spatially heterogeneous agricultural landscapes (Thorp & Tian, 2017) [63] .

Key Remote Sensing Applications

Remote sensing plays an important role in crop growth monitoring by assessing canopy structure, biomass accumulation, and phenological development across crop growth stages (Dorigo et al., 2017) [58] . Soil moisture estimation using microwave and thermal sensors helps evaluate water availability and irrigation requirements under semi-arid climatic conditions (Wagner et al., 2017) [65] . Detection of nutrient deficiency symptoms through spectral reflectance patterns supports early identification of crop stress caused by nitrogen or micronutrient limitations (Mutanga & Skidmore, 2018) [61] . Remote sensing imagery is also widely used for pest and disease identification by detecting abnormal crop reflectance signatures associated with pathogen infection or insect damage (Mahlein, 2018) [60] . Yield prediction models based on satellite-derived vegetation indices improve estimation accuracy by analyzing temporal crop growth variability (Bolton & Friedl, 2017) [56] . Drought stress assessment using thermal and vegetation indices helps identify water stress conditions and supports timely irrigation interventions (AghaKouchak et al., 2018) [53] . Vegetation indices such as NDVI (Normalized Difference Vegetation Index) are widely used to assess crop vigor, biomass accumulation, and photosynthetic activity using spectral reflectance characteristics of plant canopies (Tucker, 2017) [64] . Remote sensing provides high-resolution spatial datasets that enable monitoring of field variability and improve input-use efficiency through site-specific management strategies in semi-arid regions (Atzberger, 2017) [54] . Satellite platforms such as Sentinel and Landsat provide continuous and repetitive coverage, supporting precision irrigation scheduling and nutrient management decisions through time-series data analysis (Drusch et al., 2017) [59] . Integration of remote sensing data with decisionsupport tools improves sustainability and productivity of modern agricultural systems (Zhang et al., 2019) [66] .

Role of Artificial Intelligence in Precision Agronomy

Artificial Intelligence (AI) plays a significant role in analyzing large and complex datasets generated from Geographic Information System (GIS) and remote sensing platforms for improved agricultural decision-making (Russell & Norvig, 2021) [77] . AI techniques enable efficient processing of multi-source agricultural data, supporting precision agronomy through data-driven insights and automation of crop management practices (Sharma et al., 2020) [78] . Machine learning and deep learning algorithms are widely used for prediction, classification, clustering, and optimization of crop production strategies under varying environmental conditions (Elavarasan & Vincent, 2020) [69] . AI-based systems improve the accuracy and efficiency of agricultural operations by identifying patterns and relationships within large datasets collected from sensors, satellites, and field observations (Jiang et al., 2021) [71] .

Major AI Techniques Used in Agriculture

Artificial Neural Networks (ANN) are commonly applied for crop yield prediction, soil property estimation, and irrigation scheduling due to their ability to model nonlinear relationships among agricultural variables (Kaul et al., 2018) [72] . Random Forest (RF) algorithms are widely used for crop classification, soil variability mapping, and prediction of agricultural parameters because of their high accuracy and robustness to noisy datasets (Belgiu & Drăguţ, 2017) [68] . Support Vector Machine (SVM) models are effective in classification of crop types, disease detection, and estimation of soil moisture conditions using spectral datasets (Mountrakis et al., 2018) [75] . Convolutional Neural Networks (CNN) are extensively applied for image-based crop monitoring, pest identification, and disease detection using high-resolution remote sensing imagery (Kamilaris & Prenafeta-Boldú, 2018) [131,73] . Deep learning models improve automation in agricultural decision-making by analyzing complex relationships among climatic, soil, and crop growth parameters (LeCun et al., 2019) [74] . AI models process large datasets obtained from satellite imagery, UAV data, and sensor networks to identify crop stress conditions such as drought stress, nutrient deficiency, and pest infestation at early growth stages (Singh et al., 2020) [79] . Predictive models based on AI algorithms improve crop yield forecasting accuracy and help optimize irrigation scheduling under water-limited environments (Jeong et al., 2017) [70] . AI-driven analytics assist in identifying spatial variability in crop growth and support efficient management of agricultural inputs (Pathak et al., 2019) [76] . Integration of AI with remote sensing technologies enhances the precision of crop classification, stress detection, and resource optimization in precision farming systems (Zhu et al., 2018) [80] . Adoption of AIbased decision support systems contributes to sustainable intensification and climate-resilient agriculture in semi-arid regions (Aggarwal et al., 2018) [67] .

Integration of Gis, Remote Sensing and Ai

Integration of Geographic Information System (GIS), Remote Sensing (RS), and Artificial Intelligence (AI) technologies creates an advanced decision support system that enhances precision agronomy through accurate and data-driven farm management strategies (Khanna & Kaur, 2019) [86] . Combining spatial datasets from GIS with realtime satellite imagery and machine learning algorithms enables comprehensive analysis of crop variability, soil conditions, and climatic risks (Misra et al., 2020) [88] . Integrated digital platforms support improved decisionmaking by transforming complex agricultural datasets into actionable insights for efficient crop management (Raj et al., 2021) [90] . The synergy between GIS, RS, and AI helps optimize agricultural inputs and improves productivity under resource-limited semi-arid environments (Patel et al., 2020) [89] .

Integrated Applications

Site-specific nutrient management is enhanced through integration of spatial soil fertility maps with AI-based recommendation models, allowing precise fertilizer application across variable field conditions (Bongiovanni et al., 2017) [114,82] . Precision irrigation scheduling becomes more efficient when remote sensing-based soil moisture data are combined with predictive AI algorithms to determine optimal irrigation timing and quantity (Smith et al., 2018) [92] . Crop yield prediction models developed using integrated datasets improve forecasting accuracy by analyzing relationships among climate variables, soil parameters, and crop growth patterns (Haghverdi et al., 2018) [85] . Climate risk assessment tools based on GIS and AI help identify drought-prone areas and develop adaptive crop management strategies to minimize yield losses (Kourgialas & Karatzas, 2017) [87] . Weed and pest detection systems utilize highresolution imagery combined with deep learning algorithms to detect crop stress symptoms and recommend targeted interventions (Slaughter et al., 2018) [91] . Soil quality mapping using integrated spatial technologies helps evaluate soil health indicators and supports sustainable land management practices (Arrouays et al., 2017) [81] . UAV-based imaging integrated with machine learning models enables real-time crop monitoring and rapid detection of crop stress conditions, improving decisionmaking efficiency for farmers and researchers (Tsouros et al., 2019) [93] . Integration of GIS, RS, and AI technologies contributes to sustainable agriculture by reducing excessive input use, minimizing environmental pollution, and improving resource-use efficiency (Gebbers et al., 2017) [116,84] . Data-driven agricultural management systems enhance productivity while maintaining ecological balance in semiarid ecosystems (Finger et al., 2019) [83] . Adoption of integrated digital agriculture tools supports climate-resilient farming systems and long-term sustainability of crop production (Walter et al., 2017) [94] .

Applications in Crop Management in Semi-arid Regions Precision Irrigation Management

Efficient irrigation management is critical in semi-arid regions where limited water availability significantly restricts crop productivity and sustainability (Fereres & Soriano, 2017) [100] . Remote sensing technologies enable estimation of evapotranspiration rates and soil moisture conditions using thermal and multispectral imagery, supporting accurate irrigation planning (Allen et al., 2018) [95] . Satellite-derived indicators provide continuous monitoring of crop water requirements across spatially variable fields (Bastiaanssen et al., 2017) [96] . AI-based predictive models analyze climatic variables, soil properties, and crop growth parameters to determine optimal irrigation timing and quantity (Nhamo et al., 2020) [106] . Precision irrigation systems improve water-use efficiency, reduce water wastage, and enhance crop productivity under moisture-limited environments (Jones, 2019) [117] .

Nutrient Management

Soil fertility variability is a major constraint in semi-arid agriculture, requiring efficient nutrient management strategies to sustain crop productivity (Srinivasarao et al., 2019) [112] . GIS-based spatial maps help identify variability in soil nutrient distribution, enabling site-specific fertilizer recommendations (Heckman & Kamprath, 2018) [101] . Variable rate fertilizer application supported by spatial technologies improves nutrient-use efficiency and reduces excessive fertilizer use (Raun et al., 2017) [111] . Precision nutrient management practices minimize nutrient losses through leaching and volatilization, thereby reducing environmental pollution (Zhang et al., 2017) [122,113] . Improved nutrient management enhances crop growth, yield stability, and soil health in semi-arid ecosystems (Bindraban et al., 2018) [97] .

Weed and Pest Management

Early detection of weeds and pests is essential to minimize crop losses and reduce reliance on blanket pesticide application (Oerke, 2018) [107] . Remote sensing imagery helps identify spectral variations associated with weed infestation and pest damage at early growth stages (Huang et al., 2018) [102] . High-resolution imagery obtained from UAVs improves detection accuracy of spatial weed distribution across agricultural fields (Peña et al., 2017) [109] . AI-based classification models analyze crop stress symptoms and differentiate between pest damage, nutrient deficiency, and water stress conditions (Mohanty et al., 2019) [105] . Precision pest management strategies reduce pesticide use, lower production costs, and minimize environmental contamination (Popp et al., 2018) [110] .

Crop Yield Prediction

Crop yield prediction is an important component of precision agronomy that supports farm planning and risk management decisions (Lobell & Burke, 2017) [104] . Machine learning algorithms analyze historical weather data, soil characteristics, and crop growth parameters to estimate yield variability across spatially heterogeneous fields (Pantazi et al., 2018) [108] . Integration of climatic, spectral, and management datasets improves accuracy of crop yield forecasting models (Jeong et al., 2018) [103] . Yield prediction models help farmers make informed decisions regarding harvesting, storage, and market planning (Cai et al., 2019) [98] . Accurate yield forecasting enhances economic stability and improves resource allocation efficiency in semi-arid farming systems (Doraiswamy et al., 2017) [99] .

Advantages of Precision Agronomy in Semi-arid Regions

Precision agronomy plays a significant role in improving agricultural productivity and sustainability in semi-arid regions where water scarcity, soil variability, and climate uncertainty limit crop performance (Gebbers & Adamchuk, 2017) [116,84] . Adoption of advanced technologies such as GIS, remote sensing, and Artificial Intelligence enables efficient resource management through site-specific crop management practices (Zhang et al., 2018) [123,39] . Precision agriculture supports sustainable intensification by increasing crop yields while conserving natural resources and minimizing environmental degradation (Tilman et al., 2017) [23] .

Key Advantages

Improved water-use efficiency: Water is the most limiting factor in semi-arid agriculture. Precision irrigation systems use real-time soil moisture data, evapotranspiration estimates, and climatic parameters to optimize irrigation scheduling (Fereres & Soriano, 2017) [100] . Efficient irrigation management reduces water losses and enhances crop water productivity (Jones, 2019) [117] .

Reduced fertilizer cost: Spatial soil fertility mapping helps farmers apply fertilizers only where required, avoiding excess application and reducing input costs (Robert, 2018) [128, 121] . Variable rate technology improves nutrient-use efficiency and prevents nutrient wastage in heterogeneous soils (Raun et al., 2017) [111] .

Increased crop productivity: Precision agronomy enables timely decision-making regarding irrigation, nutrient application, and pest management, resulting in improved crop growth and yield stability (Bongiovanni & Lowenberg-DeBoer, 2017) [114,82] . Site-specific management enhances productivity even under resource constraints (Finger et al., 2019) [83] .

Early stress detection: Remote sensing tools help identify crop stress caused by drought, nutrient deficiency, or pest infestation at early growth stages (Mulla, 2018) [49] . Early detection allows farmers to take corrective measures before severe yield losses occur (Zhang & Kovacs, 2017) [122,113] .

Climate-resilient agriculture:

Precision farming technologies support climate adaptation by providing realtime monitoring of crop and weather conditions (Walter et al., 2017) [94] . Data-driven decision support systems help farmers manage climate risks and improve resilience to drought and temperature variability (Lobell et al., 2018) [118] .

Reduced environmental impact: Efficient input management reduces excessive use of fertilizers, pesticides, and irrigation water, minimizing environmental pollution and soil degradation (Tilman et al., 2017) [23] . Precision agriculture contributes to sustainable land management and conservation of natural resources (Gebbers & Adamchuk, 2017) [116,84] . Precision agronomy technologies enhance productivity while conserving water, soil, and energy resources, thereby supporting sustainable agricultural development in semi-arid ecosystems (Zhang et al., 2018) [123, 39] .

Challenges and Limitations

Despite its significant benefits, adoption of precision agronomy technologies in semi-arid regions faces several technical, economic, and infrastructural challenges that limit widespread implementation (Lowenberg-DeBoer & Erickson, 2019) [126,21] . Advanced technologies such as GIS, remote sensing, and Artificial Intelligence require skilled manpower, financial investment, and reliable digital infrastructure, which may not always be available to smallholder farmers (Finger et al., 2019) [83] . Limited accessibility and affordability of digital tools restrict the adoption of precision farming practices in developing agricultural systems (Klerkx et al., 2019) [125] .

Major Challenges

 High initial investment cost: Precision agriculture technologies require substantial investment in sensors, drones, GPS-enabled machinery, and data processing software (Robert et al., 2018) [128,121] . Small and marginal farmers may find it difficult to afford such technologies, particularly in resource-constrained semiarid regions (Lowenberg-DeBoer & Erickson, 2019) [126, 21] . High capital costs often delay adoption of modern digital farming tools (Tey & Brindal, 2017) [129] .  Lack of technical knowledge: Effective use of GIS, remote sensing, and AI tools requires technical expertise in data interpretation and digital decisionmaking (Klerkx et al., 2019) [125] . Many farmers lack training in precision agriculture technologies, limiting their ability to utilize digital advisory systems (Eastwood et al., 2017) [124] . Capacity-building and training programmes are essential for improving technology adoption (Zhang et al., 2018) [123,39] .  Limited access to high-resolution data: Highresolution satellite imagery and UAV-based data may not always be accessible due to cost, licensing restrictions, or limited availability (Atzberger, 2017) [54] . Inadequate spatial resolution affects the accuracy of crop monitoring and decision-making processes (Mulla, 2018) [49] . Data limitations reduce the efficiency of precision management strategies (Zhang & Kovacs, 2017) [122,113] .  Poor internet connectivity in rural areas: Reliable internet connectivity is essential for real-time data transmission and cloud-based decision support systems (Wolfert et al., 2017) [12] . Many semi-arid agricultural regions experience weak digital infrastructure, limiting access to online precision farming platforms (Klerkx et al., 2019) [125] . Lack of connectivity reduces the effectiveness of IoT-based agricultural monitoring systems (Misra et al., 2020) [88] .  Complexity of data interpretation: Precision agriculture generates large volumes of spatial and temporal datasets that require advanced analytical tools for interpretation (Gebbers & Adamchuk, 2017) [116,84] .

Farmers may find it difficult to translate complex datasets into practical management decisions (Eastwood et al., 2017) [124] . User-friendly decision support systems are required to simplify data interpretation and improve adoption (Lowenberg-DeBoer & Erickson, 2019) [126,21] .  Adoption of digital agriculture tools remains limited among smallholder farmers due to financial constraints, limited awareness, and lack of technical support (Tey & Brindal, 2017) [129] . Bridging the digital divide through government support, training programmes, and affordable technologies is essential for improving adoption of precision agronomy practices in semi-arid regions (Klerkx et al., 2019) [125] .

Future Research Directions

Future research in precision agronomy should focus on developing advanced, affordable, and scalable technologies that enhance productivity and sustainability in semi-arid regions (Gebbers & Adamchuk, 2017) [116,84] . Rapid advancements in digital agriculture, artificial intelligence, and big data analytics are transforming traditional crop management practices into data-driven decision systems (Wolfert et al., 2017) [12] . Research efforts are increasingly directed toward improving accessibility, reducing costs, and enhancing the efficiency of precision agriculture technologies for smallholder farming systems (Klerkx et al., 2019) [125] . [132] . Low-cost sensing devices enable continuous monitoring of field conditions and support real-time decision-making (Shamshiri et al., 2018) [137] . Cost-effective sensor technologies will increase accessibility and promote largescale adoption of digital agriculture tools (Ray et al., 2017) [135] .

Key

Integration of IoT with AI-based models: Integration of Internet of Things (IoT) networks with artificial intelligence enables automated data collection, analysis, and farm management recommendations (Misra et al., 2020) [88] . Smart farming systems combine sensor data, satellite imagery, and machine learning algorithms to optimize irrigation, fertilization, and pest management decisions (Zhang et al., 2018) [123,39] . AI-enabled IoT systems improve resource-use efficiency and enhance crop productivity under climate variability (Wolfert et al., 2017) [12] .

Climate-resilient crop management strategies: Climate change significantly affects crop productivity in semi-arid regions due to increased temperature variability and irregular rainfall patterns (Lobell et al., 2018) [118] . Future research should focus on developing adaptive crop management practices using climate-smart decision support tools (Raza et al., 2019) [136] . Precision agronomy technologies help improve resilience through early stress detection and adaptive input management strategies (Finger et al., 2019) [83] .

Big data analytics for agriculture: Big data analytics plays a crucial role in analyzing large agricultural datasets obtained from sensors, satellites, and historical farm records (Kamilaris et al., 2018) [131,73] . Advanced data mining techniques help identify patterns in crop growth, soil variability, and weather conditions (Wolfert et al., 2017) [12] . Data-driven insights improve decision-making accuracy and reduce production risks (Liakos et al., 2018) [7] .

Mobile-based decision support systems: Mobile-based advisory platforms provide real-time crop recommendations to farmers, improving accessibility of precision agriculture technologies (Klerkx et al., 2019) [125] . Smartphone applications integrated with AI models help farmers monitor crop health, irrigation requirements, and nutrient status (Pivoto et al., 2018) [134] . Mobile-based systems are particularly useful in rural areas where extension services are limited (Aker, 2018) [130] .

Real-time crop monitoring tools: Emerging technologies such as UAVs, satellite imaging, and IoT sensors enable real-time crop monitoring and early identification of crop stress conditions (Zhang & Kovacs, 2017) [122,113] . Continuous monitoring improves crop productivity by enabling timely agronomic interventions (Mulla, 2018) [49] . Real-time analytics enhance farm management efficiency and reduce yield variability (Shamshiri et al., 2018) [137] . Emerging technologies such as cloud computing, artificial intelligence, and big data analytics will further improve efficiency, scalability, and sustainability of precision agriculture systems in semi-arid environments (Kamilaris et al., 2018) [131,73] . Continued interdisciplinary research is essential to develop affordable and user-friendly digital agriculture tools that support climate-resilient farming systems (Klerkx et al., 2019) [125] .

Conclusion

Precision agronomy is transforming agricultural practices in semi-arid regions by enabling site-specific crop management through advanced technologies such as Geographic Information Systems (GIS), remote sensing, and Artificial Intelligence (AI) (Gebbers & Adamchuk, 2017) [116, 84] . These technologies provide accurate spatial and temporal information about crop growth, soil variability, and climatic conditions, allowing farmers to make informed management decisions (Zhang et al., 2018) [123,39] . Precision agriculture improves crop productivity by optimizing the use of essential inputs such as water, fertilizers, and pesticides, thereby reducing input wastage and enhancing resource-use efficiency (Tilman et al., 2017) [23] . Integration of spatial technologies with AI-based decision support systems plays a crucial role in improving agricultural sustainability in water-limited environments (Wolfert et al., 2017) [12] . Data-driven crop management practices help farmers monitor crop health, predict yield variability, and respond effectively to climate-related stresses such as drought and temperature fluctuations (Lobell et al., 2018) [118] . Advanced analytical tools enable early detection of crop stress, improving timely interventions and minimizing production risks (Mulla, 2018) [49] . Adoption of precision agriculture practices contributes to climate-resilient farming systems by supporting efficient water management, improved nutrient-use efficiency, and sustainable soil health management (Finger et al., 2019) [83] . These technologies enhance agricultural productivity while reducing environmental degradation caused by excessive use of chemical inputs (Walter et al., 2017) [94] . Precision agronomy supports sustainable intensification by producing more food using limited natural resources (Tilman et al., 2017) [23] .

In semi-arid regions, where agricultural productivity is highly influenced by water scarcity and climatic variability, precision agronomy provides innovative solutions for improving crop performance and farm profitability (Zhang et al., 2018) [123,39] . Adoption of digital agriculture technologies can significantly enhance food security, promote environmental sustainability, and ensure long-term resilience of agricultural systems (Gebbers & Adamchuk, 2017) [116,84] . Continued research, policy support, and farmer

References

1. Bongiovanni R, Lowenberg-Deboer J. Precision agriculture and sustainability. Precision Agriculture. 2018;5:359-387.
2. Burrough PA, McDonnell RA. Principles of geographical information systems. Oxford: Oxford University Press; 2018.
3. FAO. Climate change and food security in dryland agriculture. Rome: Food and Agriculture Organization of the United Nations; 2021.
4. Gebbers R, Adamchuk VI. Precision agriculture and food security. Science. 2019;327:828-831.
5. IPCC. Climate change 2022: impacts, adaptation and vulnerability. Intergovernmental Panel on Climate Change; 2022.
6. Lal R. Soil degradation and sustainable land management. Boca Raton: CRC Press; 2020.
7. Liakos KG, et al. Machine learning in agriculture: a review. Sensors. 2018;18(8):2674.
8. Pierce FJ, Nowak P. Aspects of precision agriculture. Advances in Agronomy. 2019;67:1-85.
9. Rockström J, et al. Managing water in rainfed agriculture. Agricultural Water Management. 2017;97:543-550.
10. Rouse JW, et al. Monitoring vegetation systems using NDVI. NASA Earth Resources Technology Satellite Program; 1974.
11. Thenkabail PS. Remote sensing handbook for agricultural applications. Boca Raton: CRC Press; 2018.
12. Wolfert S, Ge L, Verdouw C, Bogaardt MJ. Big data in smart farming. Agricultural Systems. 2017;153:69-80.
13. Zhang N, Wang M, Wang N. Precision agriculture technologies for crop management. Computers and Electronics in Agriculture. 2021;36:113-132.
14. Balafoutis A, Beck B, Fountas S, Tsiropoulos Z, Vangeyte J, Van der Wal T, et al. Precision agriculture technologies positively contributing to sustainable farming systems. Sustainability. 2017;9:1339.
15. Bramley R. Lessons from nearly 20 years of precision agriculture research. Precision Agriculture. 2019;20:119.
16. Chlingaryan A, Sukkarieh S, Whelan B. Machine learning approaches for crop yield prediction. Computers and Electronics in Agriculture. 2018;151:61-69.
17. Dai A. Increasing drought under global warming in observations and models. Nature Climate Change. 2018;3:52-58.
18. Foley JA, et al. Solutions for a cultivated planet. Nature. 2019;478:337-342.
19. Gebbers R, et al. Precision agriculture adoption and environmental sustainability. Agronomy Journal. 2020;112:1-15.
20. Khanal S, Fulton J, Shearer S. An overview of current and potential applications of UAV in agriculture. Computers and Electronics in Agriculture. 2020;173:105418.
21. Lowenberg-DeBoer J, Erickson B, Widmar D. Economics of precision agriculture adoption. Annual Review of Resource Economics. 2019;11:341-362.
22. McBratney A, Whelan B, Ancev T, Bouma J. Future directions of precision agriculture. Precision Agriculture. 2018;6:7-23.
23. Tilman D, Balzer C, Hill J, Befort B. Global food demand and sustainable intensification. Proceedings of the National Academy of Sciences of the United States of America. 2017;108:20260-20264.
24. Tomlinson R. Thinking about GIS: geographic information system planning. Redlands: ESRI Press; 2017.
25. UNEP. Global environment outlook for dryland ecosystems. United Nations Environment Programme; 2021.
26. Xue J, Su B. Significant remote sensing vegetation indices. Sensors. 2017;17:165.
27. Adamchuk VI, Hummel JW, Morgan MT, Upadhyaya SK. On-the-go soil sensors for precision agriculture. Computers and Electronics in Agriculture. 2018;44:7191.
28. Corwin DL, Lesch SM. Applications of soil electrical conductivity in precision agriculture. Agronomy Journal. 2019;97:455-471.
29. D'Odorico P, Bhattachan A, Davis KF, Ravi S, Runyan CW. Global desertification: drivers and feedbacks. Advances in Water Resources. 2018;51:326-344.
30. Falkenmark M. Water scarcity and food production challenges. International Journal of Water Resources Development. 2017;33:147-159.
31. Fixen P, Brentrup F, Bruulsema T, Garcia F, Norton R, Zingore S. Nutrient management for sustainable crop production. Global Food Security. 2019;12:29-37.
32. Hatfield JL, Prueger JH. Temperature extremes and crop productivity. Weather and Climate Extremes. 2019;10:4-10.
33. ICRISAT. Crops for dryland systems. International Crops Research Institute for the Semi-Arid Tropics; 2019.
34. Lal R, Negassa W, Lorenz K. Carbon sequestration in soil. Agronomy for Sustainable Development. 2018;35:635-651.
35. Minasny B, McBratney AB. Soil organic carbon and soil health. Geoderma. 2018;292:59-68.
36. Nicholson SE. Climate variability in semi-arid regions. Wiley Interdisciplinary Reviews: Climate Change. 2018;5:135-147.
37. Passioura J. Improving water-use efficiency in agriculture. Agricultural Water Management. 2017;80:176-186.
38. Reynolds JF, et al. Global desertification and dryland sustainability. Science. 2017;316:847-851.
39. Zhang C, Kovacs JM. The application of small UAVs in precision agriculture. Precision Agriculture. 2018;13:693-712.
40. Basso B, Cammarano D, Carfagna E. Review of crop yield forecasting methods and applications. European Journal of Agronomy. 2019;82:15-29.
41. Eastman JR. IDRISI GIS and image processing software guide. Clark Labs; 2017.
42. FAO. Land suitability assessment for agricultural planning. Food and Agriculture Organization; 2022.
43. Hartemink AE. Soil fertility decline in the tropics. Advances in Agronomy. 2018;89:179-210.
44. Heuvelink GBM, Webster R. Modelling soil variation: past, present, and future. Geoderma. 2019;100:269-301.
45. Jones JW, Hoogenboom G, Porter CH, Boote KJ, Hunt LA. Decision support system for agrotechnology transfer. Agricultural Systems. 2017;74:43-59.
46. Longley PA, Goodchild MF, Maguire DJ, Rhind DW. Geographic information systems and science. Wiley; 2019.
47. Malczewski J. GIS-based multicriteria decision analysis. International Journal of Geographical Information Science. 2017;20:703-726.
48. McBratney A, Minasny B, Whelan B. Precision agriculture and spatial variability analysis. Precision Agriculture. 2017;6:7-23.
49. Mulla DJ. Spatial variability and precision agriculture technologies. Precision Agriculture. 2018;4:7-16.
50. Robert P. Precision agriculture: a challenge for crop nutrition management. Plant and Soil. 2017;247:143149.
51. Tomlinson Calkins H, Marble D. Computer handling of geographical data. UNESCO Press; 2018.
52. Vicente-Serrano SM, Beguería S, López-Moreno JI. Drought monitoring using GIS and remote sensing. Journal of Climate. 2019;23:1696-1718.
53. AghaKouchak A, Huning LS, Chiang F. Global drought monitoring using satellite observations. Nature Reviews Earth and Environment. 2018;1:19-32.
54. Atzberger C. Advances in remote sensing of agriculture. Remote Sensing. 2017;5:5498-5528.
55. Blackburn GA. Hyperspectral remote sensing of plant pigments. Journal of Experimental Botany. 2018;58:855-867.
56. Bolton DK, Friedl MA. Forecasting crop yield using remotely sensed vegetation indices. Agricultural and Forest Meteorology. 2017;173:74-84.
57. Campbell JB, Wynne RH. Introduction to remote sensing. Guilford Press; 2017.
58. Dorigo W, Zurita-Milla R, de Wit A, Brazile J, Singh R, Schaepman M. A review on reflective remote sensing for crop monitoring. International Journal of Applied Earth Observation and Geoinformation. 2017;64:12-25.
59. Drusch M, et al. Sentinel-2 ESA mission for land monitoring. Remote Sensing of Environment. 2017;120:25-36.
60. Mahlein AK. Plant disease detection using imaging sensors. Annual Review of Phytopathology. 2018;54:459-482.
61. Mutanga O, Skidmore A. Hyperspectral remote sensing for crop nutrient estimation. Remote Sensing of Environment. 2018;95:21-33.
62. Pettorelli N, et al. Satellite remote sensing for applied ecology. Trends in Ecology and Evolution. 2018;29:117-126.
63. Thorp KR, Tian LF. Remote sensing in precision agriculture. Computers and Electronics in Agriculture. 2017;61:2-19.
64. Tucker CJ. Red and photographic infrared linear combinations for vegetation monitoring. Remote Sensing of Environment. 2017;8:127-150.
65. Wagner W, et al. Soil moisture retrieval from satellite sensors. Hydrology and Earth System Sciences. 2017;11:717-739.
66. Zhang J, Pu R, Huang W. Crop stress detection using remote sensing. International Journal of Remote Sensing. 2019;40:135-153.
67. Aggarwal P, Jain S, Pathak H. Climate resilient agriculture using smart technologies. Agricultural Systems. 2018;165:98-107.
68. Belgiu M, Drăguţ L. Random forest in remote sensing classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2017;114:24-31.
69. Elavarasan D, Vincent DR. Artificial intelligence in agriculture: a review. Journal of Artificial Intelligence Research. 2020;65:1-15.
70. Jeong JH, Resop JP, Mueller ND, Fleisher DH, Yun K, Butler EE, et al. Random forest yield prediction in agriculture. Agricultural and Forest Meteorology. 2017;231:39-47.
71. Jiang Y, Li C, Paterson AH, Robertson JS. Deep learning for image-based crop phenotyping. Trends in Plant Science. 2021;25:123-134.
72. Kaul M, Hill RL, Walthall C. Artificial neural networks for crop yield prediction. Agricultural Systems. 2018;85:1-18.
73. Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: a survey. Computers and Electronics in Agriculture. 2018;147:70-90.
74. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2019;521:436-444.
75. Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing. 2018;66:247-259.
76. Pathak H, Brown P, Best T. Data-driven agriculture and climate resilience. Agronomy Journal. 2019;111:1-9.
77. Russell S, Norvig P. Artificial intelligence: a modern approach. Pearson; 2021.
78. Sharma A, Jain A, Gupta P, Chowdary V. Machine learning applications in agriculture. Computers and Electronics in Agriculture. 2020;169:105221.
79. Singh A, Ganapathysubramanian B, Sarkar S, Mueller D. Deep learning for plant stress phenotyping. Plant Methods. 2020;12:1-15.
80. Zhu X, Miao Y, Wang H. Artificial intelligence in precision agriculture. Computers and Electronics in Agriculture. 2018;153:69-81.
81. Arrouays D, McKenzie N, Hempel J, Richer-de-Forges A, McBratney A. Global soil information systems. CRC Press; 2017.
82. Bongiovanni R, Lowenberg-DeBoer J, Erickson B. Precision nutrient management systems. Agronomy Journal. 2017;109:1-10.
83. Finger R, Swinton SM, El Benni N, Walter A. Precision farming at the nexus of agricultural production and environment. Annual Review of Resource Economics. 2019;11:313-335.
84. Gebbers R, Schellberg J, Lock R. Precision agriculture technologies for improved crop productivity. Agronomy. 2017;7:45.
85. Haghverdi A, Washington-Allen R, Leib B. Machine learning applications for crop yield prediction. Agricultural Water Management. 2018;199:93-102.
86. Khanna A, Kaur S. Evolution of internet of things applications in agriculture. Computers and Electronics in Agriculture. 2019;165:104859.
87. Kourgialas NN, Karatzas GP. A review of GIS-based drought assessment. Water Resources Management. 2017;29:431-449.
88. Misra NN, Dixit Y, Al-Mallahi A, Bhullar MS, Upadhyay R, Martynenko A. IoT, big data and AI in agriculture. Trends in Food Science and Technology. 2020;100:69-80.
89. Patel KK, Kar A, Jha SN, Khan MA. Machine vision for quality assessment in agriculture. Computers and Electronics in Agriculture. 2020;159:85-95.
90. Raj R, Kar S, Das S. Smart farming technologies for sustainable agriculture. Sustainable Computing. 2021;28:100321.
91. Slaughter DC, Giles DK, Downey D. Autonomous robotic weed control systems. Computers and Electronics in Agriculture. 2018;61:63-78.
92. Smith R, Baillie C, McCarthy A. Decision support systems for irrigation management. Agricultural Water Management. 2018;98:1-9.
93. Tsouros DC, Bibi S, Sarigiannidis PG. UAV-based applications in agriculture. Information. 2019;10:349.
94. Walter A, Finger R, Huber R, Buchmann N. Smart farming and sustainability. Proceedings of the National Academy of Sciences of the United States of America. 2017;114:6148-6150.
95. Allen RG, Pereira LS, Raes D, Smith M. Crop evapotranspiration guidelines for computing crop water requirements. FAO Irrigation and Drainage Paper 56; 2018.
96. Bastiaanssen WGM, Molden DJ, Makin IW. Remote sensing for irrigated agriculture management. Agricultural Water Management. 2017;80:87-104.
97. Bindraban PS, Dimkpa C, Pandey R. Improving nutrient use efficiency in agriculture. Agronomy for Sustainable Development. 2018;35:1-12.
98. Cai Y, Guan K, Lobell D, Potgieter A, Wang S, Peng B, et al. Integrating satellite and climate data for crop yield prediction. Remote Sensing of Environment. 2019;222:1-14.
99. Doraiswamy PC, Moulin S, Cook PW, Stern A. Crop yield assessment from remote sensing. Agricultural and Forest Meteorology. 2017;124:1-14.
100. Fereres E, Soriano MA. Deficit irrigation for reducing water use in agriculture. Journal of Experimental Botany. 2017;58:147-159.
101. Heckman JR, Kamprath EJ. Nutrient management for crop production. Agronomy Journal. 2018;92:356-362.
102. Huang Y, Reddy KN, Fletcher RS, Pennington D. UAV remote sensing for weed detection. Weed Technology. 2018;32:1-7.
103. Jeong JH, Resop JP, Mueller ND, Fleisher DH, Yun K, Butler EE, et al. Machine learning for yield prediction. Agricultural and Forest Meteorology. 2018;231:39-47.
104. Lobell DB, Burke MB. Climate impacts on crop productivity. Annual Review of Environment and Resources. 2017;35:435-461.
105. Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science. 2019;7:1419.
106. Nhamo L, Magidi J, Nyamugama A, Clulow A. Precision irrigation and water management technologies. Water. 2020;12:1-18.
107. Oerke EC. Crop losses due to pests and diseases. Journal of Agricultural Science. 2018;144:31-43.
108. Pantazi XE, Moshou D, Alexandridis T, Whetton RL, Mouazen AM. Wheat yield prediction using machine learning. Computers and Electronics in Agriculture. 2018;121:57-65.
109. Peña JM, Torres-Sánchez J, Serrano-Pérez A, de Castro AI, López-Granados F. Weed mapping using UAV imagery. Precision Agriculture. 2017;14:1-17.
110. Popp J, Pető K, Nagy J. Pesticide productivity and environmental impacts. Agronomy for Sustainable Development. 2018;33:243-255.
111. Raun WR, Solie JB, Johnson GV. Improving nitrogen use efficiency in cereals. Agronomy Journal. 2017;94:815-820.
112. Srinivasarao C, Venkateswarlu B, Lal R, Singh AK, Kundu S. Soil fertility management in dryland agriculture. Advances in Agronomy. 2019;89:179-210.
113. Zhang X, Davidson EA, Mauzerall DL, Searchinger TD, Dumas P, Shen Y. Managing nitrogen for sustainable development. Nature. 2017;528:51-59.
114. Bongiovanni R, Lowenberg-DeBoer J. Precision agriculture and sustainability. Crop Science. 2017;44:124-132.
115. Finger R, Swinton S, El Benni N, Walter A. Precision farming and agricultural sustainability. Annual Review of Resource Economics. 2019;11:313-335.
116. Gebbers R, Adamchuk VI. Precision agriculture technologies for crop management. Science. 2017;327:828-831.
117. Jones HG. Irrigation scheduling using precision agriculture tools. Agricultural Water Management. 2019;64:1-10.
118. Lobell DB, Schlenker W, Costa-Roberts J. Climate trends and global crop production. Science. 2018;333:616-620.
119. Mulla DJ. Twenty five years of remote sensing in precision agriculture. Biosystems Engineering. 2018;114:358-371.
120. Raun WR, Solie JB, Stone ML. Improving nitrogen use efficiency in cereals. Agronomy Journal. 2017;94:815820.
121. Robert PC. Precision agriculture: a challenge for crop nutrition management. Plant and Soil. 2018;247:143149.
122. Zhang C, Kovacs JM. The application of small UAVs for precision agriculture. Precision Agriculture. 2017;13:693-712.
123. Zhang N, Wang M, Wang N. Precision agriculture technologies for crop management. Computers and Electronics in Agriculture. 2018;36:113-132.
124. Eastwood C, Klerkx L, Nettle R, Dela Rue B. Managing socio-ethical challenges in precision agriculture. Journal of Agricultural Education and Extension. 2017;23:1-15.
125. Klerkx L, Jakku E, Labarthe P. Digital agriculture and knowledge systems. Agricultural Systems. 2019;153:69-80.
126. Lowenberg-DeBoer J, Erickson B. Setting the record straight on precision agriculture adoption. Agronomy Journal. 2019;111:1552-1569.
127. Mulla DJ. Remote sensing applications in precision agriculture. Biosystems Engineering. 2018;114:358371.
128. Robert PC, Rust RH, Larson WE. Soil-specific crop management. ASA Journal. 2018;5:1-12.
129. Tey YS, Brindal M. Adoption of precision agriculture technologies. Precision Agriculture. 2017;13:713-730.
130. Aker JC. The role of mobile phones in agricultural development. Agricultural Economics. 2018;42:631647.
131. Kamilaris A, Kartakoullis A, Prenafeta-Boldú F. Big data analytics in agriculture. Computers and Electronics in Agriculture. 2018;147:70-90.
132. Kim Y, Evans RG, Iversen WM. Remote sensing and control of irrigation systems. Computers and Electronics in Agriculture. 2019;61:1-13.
133. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture. Sensors. 2018;18:2674.
134. Pivoto D, Waquil PD, Talamini E, Finocchio CP, Dalla Corte VF, de Vargas Mores G. Scientific development of smart farming technologies. Journal of Rural Studies. 2018;59:37-46.
135. Ray PP. Internet of things for smart agriculture. Journal of Ambient Intelligence. 2017;9:1-15.
136. Raza A, Razzaq A, Mehmood SS, Zou X, Zhang X, Lv Y, et al. Impact of climate change on crops. Agronomy. 2019;9:1-21.
137. Shamshiri RR, Kalantari F, Ting KC, Thorp KR, Hameed IA, Weltzien C, et al. Advances in greenhouse automation and smart farming. Information Processing in Agriculture. 2018;5:1-15.
138. Mulla DJ. Remote sensing in precision agriculture. Biosystems Engineering. 2018;114:358-371.