Remote sensing and ai-driven innovations in contemporary agriculture and horticulture: A review for crop improvement

Introduction

Global agriculture and horticulture face pressing challenges: feeding a growing population under climate change and resource constraints demands higher productivity, resilience and efficiency. Remote sensing (RS) and AI technologies have emerged as pivotal tools to meet these challenges [1] . Remote sensing collects data on crops and environments from a distance (satellites, drones, sensors) and has been applied for decades in Earth observation. Artificial intelligence (AI), particularly machine learning (ML) and deep learning, enables automated analysis of the vast data produced by RS to extract actionable insights. The fusion of RS and AI supports precision agriculture and precision horticulture, enabling field-specific management that optimizes inputs (water, fertilizer, pesticides) and maximizes yield while minimizing environmental impact [2] . Traditional agriculture relied on manual field scouting and random sampling. By contrast, modern digital agriculture uses sensors to continuously monitor crops in space and time. Advances in spectral imaging allow measurement of plant vigor (e.g. via NDVI), moisture content (e.g. using thermal or radar) and canopy structure (LiDAR) over large areas [3] . Simultaneously, AI algorithms analyze complex sensor data to predict crop performance or detect anomalies. This combination allows early warning of stress (drought, disease), detailed mapping of field variability and data-driven decision-making on irrigation, fertilization and pest control. In horticulture, high-value fruit and vegetable crops benefit from fine-scale monitoring (for example, drone-based yield estimation in orchards or automated greenhouse environment control) [4] . The use of remote imaging for agriculture has roots before World War II, but accelerated in the mid-20th century. In the 1930s and 1940s, aerial photography from planes became a practical tool for mapping soil types and crop conditions. Visionaries like Professor J. Ralph Shay (Purdue University) recognised the potential of air and space sensing for agriculture. In 1960, the successful launch of TIROS-1 (Television Infrared Observation Satellite) demonstrated weather observation from space [5] . By 1958, the term "remote sensing" was introduced to describe this emerging discipline. In 1961, a U.S. National Research Council committee on "Aerial Survey Methods in Agriculture" was chaired by Professor Shay, bringing together experts. Early grants by NASA and USDA funded data collection and analysis projects. Robert N. Colwell (UC Berkeley) worked on manual photointerpretation for forests and crops, laying groundwork for image classification [6] . By 1966, Purdue's Laboratory for Applications of Remote Sensing (LARS) was established (led by Shay, with Dr. K. S. Fu and Dr. David Landgrebe), an interdisciplinary team integrating engineering and plant science. K.S. Fu, a pioneer in pattern recognition, advocated using computer algorithms to analyze spectral data. Landgrebe's early research pioneered the idea of using spectral signatures (rather than fine spatial detail) to identify vegetation foreshadowing modern multispectral analysis [7] . Simultaneously, artificial intelligence began to influence agricultural data analysis. Early AI research in the 1950s-60s (e.g. Frank Rosenblatt's Perceptron in 1957) was not initially agricultural. However, by the 1970s-80s, specialists applied machine learning to crop data analysis. For example, Smith et al. in the 1980s used pattern recognition to classify crop types from imagery [8] . Guy Fayad, Qingshan Liu and others contributed to the use of neural networks and decision trees in crop yield estimation and disease identification. The field of precision agriculture emerged around 1990, integrating GPS and GIS with sensor data, in this era scientists like John L. Bennetts (CSIRO, Australia) and Elizabeth Hawkins began automating yield monitors and spatial crop models [9] .

Methods and Technologies

Remote sensing and AI rely on a suite of modern technologies. This section describes the key platforms, sensor types, data processing methods and AI techniques that constitute the toolbox for agricultural and horticultural applications [10] .

Remote Sensing Platforms and Sensors

Spaceborne Satellites: Earth observation satellites provide broad coverage of agricultural regions on a regular schedule. Notable platforms include Landsat (USGS/NASA, launched 1972 onward), Sentinel-2 (ESA, launched 2015) and commercial constellations like PlanetScope. Sensors on these satellites range from simple RGB cameras to advanced multispectral and hyperspectral scanners [11] . For instance, Landsat 8/9 carries the Operational Land Imager (OLI) with six optical bands (visible to shortwave IR) at 30m resolution and the Thermal Infrared Sensor (TIRS) for thermal data. Sentinel-2 carries multispectral instruments (13 bands from visible to SWIR) at 10-60 m resolution. The freely accessible data from these satellites enable large-scale monitoring of fields (e.g. calculating NDVI for vegetation health). Other satellites include MODIS (daily, coarse ~250m resolution) for global vegetation indices, WorldView (Maxar) with very-high-resolution (0.3m) imagery and Sentinel-1 (radar) which provides C-band synthetic aperture radar (SAR) at ~10m resolution insensitive to clouds [12] .

Airborne Systems: Manned aircraft equipped with imaging sensors cover fields at intermediate scale. Fixed-wing or helicopter surveys can carry high-resolution multispectral or hyperspectral cameras (hundreds of narrow bands) and LiDAR scanners. These provide centimetre-scale mapping of large estates or research plots, used for biomass estimation or terrain modelling. Advantages include customizable flight plans and high resolution, limitations are cost, required pilots and less frequent revisits [13] .

Unmanned Aerial Vehicles (UAVs/Drones): In the last decade, UAVs have become widely used in precision agriculture and horticulture. Small drones (rotor or fixed-wing) can carry off-the-shelf cameras or specialized sensors [14,15,16] . Drones typically fly under 120m altitude, covering small to medium fields (few hectares per flight). They excel at highdetail imagery for orchard trees or experimental plots and can be deployed on demand. Drawbacks include limited flight time/battery, weather sensitivity and regulatory requirements for flight. Nonetheless, UAVs democratize precision sensing: many researchers and farmers now routinely use drone NDVI maps, weed detection and canopy analyses [17] .

Ground-Based Sensors: These include fixed towers or mobile platforms with sensors in or near fields [18,19,20] . Examples: Ground sensors provide very high-frequency, site-specific data, complementing aerial observations. They are key for precision horticulture (e.g. greenhouse climate control) and for validating remote measurements. However, they cover only limited spatial extent per deployment [21] .

Table 1: Remote Sensing Platforms and Sensors [22,23,24] Platform . The red and NIR bands are especially important since vegetation reflectance there relates to chlorophyll content and leaf structure [25] . Hyperspectral sensors break the spectrum into dozens or hundreds of narrow bands, enabling detection of subtle chemical changes (e.g., nutrient deficiencies or early disease) that broad bands might miss. Hyperspectral data are powerful for detailed analysis but require more complex processing and are less common in routine farming use due to cost and data volume [26] .

Synthetic Aperture Radar (SAR): SAR sensors (on satellites like Sentinel-1 or airborne radars) emit microwave pulses and measure backscatter. SAR penetrates clouds and provides information on surface roughness and moisture. For example, wetter soils or water in crop canopies increase backscatter intensity. SAR is used for monitoring flood risk, soil moisture and even crop structure (e.g. distinguishing crop types by their scattering signature). Integrating SAR and optical data is an active research area, especially in cloudy regions where optical imagery is often blocked [27] .

Thermal Infrared: Thermal cameras measure land surface temperature. In crops, higher canopy temperatures indicate water stress (stomata closing, less evaporative cooling). Thermal imaging is used for irrigation management and drought monitoring. It has been applied in vineyard water stress studies and to schedule irrigation in cotton and corn [28] .

Data Preprocessing: Raw sensor data require calibration and correction. This includes radiometric correction (converting raw sensor values to reflectance), atmospheric correction (removing effects of aerosols and water vapor) and geometric correction (aligning images to maps). Data preprocessing may also involve cloud masking for optical imagery. For UAVs, image stitching (orthomosaic creation) is common. Vegetation indices (like NDVI, SAVI, NDRE, etc.) are then computed from band ratios to highlight plant health metrics [29] .

Data Fusion: Combining data across platforms improves analysis. For instance, blending frequent low-resolution data with infrequent high-resolution data (or merging optical and SAR imagery) can produce spatio-temporally rich datasets. Data fusion can fill cloud-induced gaps or provide both broad context and fine detail [30] .

AI and Machine Learning Models

Analyzing remote sensing data for crop insights relies on AI/ML methods. AI algorithms translate raw or derived sensor data into actionable information: classification (e.g. crop type, disease presence), regression (e.g. predicting yield), segmentation (e.g. delineating weed patches) and forecasting (e.g. growth stages over time) [31] • Decision Tree (DT): Splits data by feature thresholds for classification or regression. Useful for categorical decisions (e.g. crop vs weed), easy to interpret, but can overfit small data [32] . • Random Forest (RF): An ensemble of many decision trees, robust to noise, handles mixed data well. Commonly used for land cover and crop classification. Requires moderate training data, larger ensembles increase computation [32] . • Support Vector Machine (SVM): Finds optimal hyperplane to separate classes. Effective for highdimensional spectral data classification. Needs labeled training data, can be slow for very large datasets, kernel selection can be tricky [33] . • K-Nearest Neighbors (KNN): Classifies a point by majority vote of nearest neighbors in feature space. Simple, no training phase, but performance drops with large datasets and many features [34] . • Naive Bayes: Probabilistic classifier assuming feature independence. Quick to train, handles noisy data, used sometimes for classifying vegetation stress. Assumption of independence can limit accuracy [34] . • K-Means Clustering: Unsupervised method grouping data into k clusters by similarity. Useful for exploratory segmentation (e.g. grouping field images by growth stage without labels). Choosing k and initial clusters can be hard, not guaranteed to find optimal clusters [35] .

• Principal Component Analysis (PCA): Not a classifier but used to reduce data dimensionality (e.g. compress hyperspectral bands to a few uncorrelated components). Speeds up other algorithms, reduces noise, however, principal components can be hard to interpret agronomically. • Linear Regression / PLS Regression: For tasks like yield prediction based on spectral indices or sensor readings. Requires continuous target data, easy to interpret coefficients, but assumes linear relationships which may not hold in complex crops [35] . • Gradient Boosting (e.g. XGBoost, LightGBM): Ensemble of weak learners trained sequentially, high accuracy in many tasks (crop yield estimation, disease risk). Strong performance but requires careful tuning and can overfit [36] . • Artificial Neural Network (ANN): Multi-layer perceptron for regression/classification on tabular features (e.g. spectral indices). Learns nonlinear relationships, requires sizable training data, "black box" model (harder to interpret) [35] . [35] .

• U-Net / Segmentation CNN: CNN architecture for pixelwise segmentation tasks (e.g. delineating maize plants or diseased leaves in an image). Accurate for mapping canopy cover or disease spread. Data-intensive (needs ground truth masks) [37] . • Recurrent Neural Network (RNN)/LSTM: Models that capture temporal sequences. Used for time-series analysis (e.g. predicting yield from vegetation index time series throughout season). Captures temporal patterns, risk of overfitting, training can be slow [36] . • YOLO / Faster R-CNN (Object Detection): Deep networks for detecting and localizing objects in images. Applied to count fruits on a tree or detect weeds from crop images. High accuracy, require annotated bounding boxes, computationally heavy [37] . • Gaussian Processes: Probabilistic regression modeling time series or spatial patterns (e.g. soil moisture trends).

Provides uncertainty estimates, but scale poorly to large data and require kernel design [33] . • Deep Belief Networks / Autoencoders: Less common but used for unsupervised feature learning from images or spectral data. Good for anomaly detection, generally supplanted by more efficient CNNs and GANs [38] .

Applications in Crops and Horticulture

Remote sensing and AI find applications across the full spectrum of crop systems. We consider both broad acre agriculture (cereals, oilseeds, pulses, etc.) and horticulture (fruits, vegetables, greenhouse crops, ornamentals), highlighting common themes and unique cases [42] .

Crop Monitoring and Yield Prediction

One of the most common applications is crop yield forecasting and mapping. By analyzing temporal sequences of vegetation indices (like NDVI or enhanced vegetation index EVI) from satellites, researchers build regression or machine learning models to predict end-of-season yield. For example, multi-year Landsat NDVI series combined with weather data feed AI models (e.g. LSTM networks) that forecast maize or wheat yield at regional scales [43] . This assists national agencies and farmers in planning harvest and markets. In the US Corn Belt, yield estimates from RS data have achieved accuracies within 5-10% of actual yields in many studies. In India and China, moderateresolution imaging and time-series analysis of paddy fields have enabled rice yield predictions weeks before harvest. SAR data (Sentinel-1) are used to monitor rice flooding and biomass, helping predict production in areas where clouds hinder optical imagery [44] . indices (NDRE, NDWI, red-edge NDVI) are frequently used features. AI models track crop growth stages. For example, time series of spectral features fed into LSTM or HMM (Hidden Markov models) can identify flowering and maturity dates. This helps schedule irrigation and inputs optimally [45,46] .

Crop condition monitoring:

Disease and Pest Detection

Identifying diseases and pests early is critical. Remote sensing provides spectral cues of plant health and AI translates them into diagnostic information. Many diseases cause localised changes: chlorosis, necrosis, or canopy structure alterations [47] . Highresolution UAV images and ground robots with camera arms detect leaf spots or wilting. Deep learning is particularly adept at image-based identification: CNNs trained on labelled images of diseased vs healthy leaves achieve high accuracy on diseases like late blight in potato or stripe rust in wheat. Hyperspectral sensors capture subtle spectral signatures of infection that may precede visible symptoms [48] . Wheat rust in Australia was detected from drone multispectral images using a Random Forest model to identify rust hotspots at early stages. Similarly, the detection of banana Black Sigatoka disease was enhanced by using hyperspectral imaging and SVM classifiers to pinpoint affected areas. Another example is pest infestation mapping: sensors combined with thermal or optical imaging (plus AI) track swarms of locusts or insect damage. For fruit crops, winged pests or larvae spots on leaves are detected using deep learning object detectors on high-res images [49] . Nutrient and Water Management is pest infestation mapping: sensors combined with thermal or optical imaging (plus AI) track swarms. Remote sensors measure proxies for nutrients and water: for example, chlorophyll reflectance relates to nitrogen content. AI models correlate spectral indices with measured soil or plant nutrient levels. As a result, farmers can create variablerate fertilizer prescriptions. UAV-based NDVI maps are often used to apply nitrogen variably across a field [50] . Water stress detection is another key area. Soil moisture sensors inform irrigation directly, but satellites like Sentinel-1 (SAR) indirectly estimate soil moisture from backscatter. Thermal imaging reveals plant canopy temperature, a strong indicator of water stress. Coupled with AI regression models, farmers can schedule irrigation more efficiently. In irrigated cotton farming, satellite data were used to map evapotranspiration via thermal and multispectral imagery. An AI model (e.g. an ANN) combined with weather data estimated water requirements, reducing irrigation by 20% while maintaining yields [51] .

Crop Mapping and Classification

Accurate maps of what crops are planted where and at what stage are valuable for commodity forecasting and management. AI classification of satellite imagery yields crop type maps. For instance, Random Forest classifiers on multi-date imagery can distinguish maize, soybean and other crops in large regions [83] . Drone imagery can classify within-field heterogeneity (e.g. patches of weed vs crop). In horticulture, crop classification may identify tree species in orchards or vegetables in fields. Highresolution WorldView data plus CNN segmentation have been used to map vineyards, orchards, or even individual tree canopies from space [52] .

Horticultural Applications

Horticulture (fruits, vegetables, ornamentals, greenhouse crops) often has higher-value produce and smaller plots. The high spatial resolution of UAVs and ground sensors is particularly useful here [53] . Applications include:

• Fruit Yield Estimation: Drones capture images of fruiting trees, AI (e.g. object detection networks like YOLO) counts fruit or clusters. This helps estimate potential yield.

Example: Counting apples in orchards or mangoes using drone imagery and CNN detectors [54] .

Flowering and Maturity Monitoring:

In crops like apples or cotton, satellite NDVI or drone images can estimate bloom density and predict harvest time. AI models calibrate flowering intensity with yield output [55] .

• Greenhouse Monitoring: Indoor horticulture uses fixed sensors and cameras (RGB, thermal) plus AI to control climate (temperature, humidity, CO₂, lighting). For example, tomato greenhouse systems use neural networks to optimize irrigation and fertigation schedules based on realtime sensor data [56] .

• Pest/Disease in High-Value Crops: In vineyards and orchards, early detection of diseases like powdery mildew or insect pests is critical. UAV multispectral imaging combined with ML models maps disease spread in vineyards, guiding targeted spraying [57] .

• Weed Management: In vegetable fields, fine-scale imaging and CNNs can identify weed seedlings among crops, allowing robotic spot-spraying or hand weeding only where needed [58] .

Cereals: In the U.S. Corn Belt, researchers used Sentinel-2 multispectral time series and a Random Forest model to predict maize yield across multiple counties, achieving ~90% accuracy. In India's Punjab region, UAV multispectral flights of wheat fields provided NDVI maps that an LSTM model used to forecast yield one month in advance, enabling better input planning [59,60] .

Rice: In China's Yangtze Delta, a combination of Sentinel-1 SAR and Sentinel-2 optical data was fed into a CNN-based model for rice field boundary detection and health classification, helping predict yields and irrigation needs. Similarly, in Southeast Asia, SAR time-series with long short-term memory (LSTM) networks have been used to map flooded rice areas and estimate production even under persistent cloud cover [61,62] .

Maize: In Brazil's Mato Grosso, Landsat imagery combined with a gradient boosting model estimated soybean and corn yields for large farms, supporting national crop forecasts. In sub-Saharan Africa (Nigeria, Ghana), drone images of maize fields have been analyzed by an SVM model to detect nutrient deficiency patches, improving local fertilizer applicatin [63] .

Soybean:

In Argentina, a deep learning pipeline (U-Net segmentation on high-res aerial images) mapped soybean canopy cover for biomass estimation. In the U.S., UAV hyperspectral scans of soy plots were used by random forest regression to predict protein content as an element of quality assessment [82,64] .

Wheat: In Australia, Landsat and MODIS NDVI data over wheat-growing regions were used with both linear regression and machine learning (random forest, XGBoost) to produce annual wheat yield maps, which informed stock market forecasts. Wheat rust disease in Canada was monitored via UAV imagery, an ANN classifier distinguished healthy vs. rustinfected plots, allowing targeted fungicide treatment [65,66] .

Vegetables: In the Netherlands, greenhouse tomato production uses a network of IoT sensors (light, humidity, CO₂) with an AI controller (ANN + rule-based logic) that optimizes lighting and ventilation, reducing energy use by 15%. In the United States, remote sensing has been applied to open-field lettuce, drone multispectral data and a convolutional neural network were used to detect early-stage downy mildew infections, alerting growers before symptoms were visible [67,68] .

Fruits (Horticulture): European vineyards have seen extensive RS+AI use. In France, drone surveys of grapevines with multispectral and thermal cameras feed random forest models that classify vines by vigor level, guiding variable irrigation. In Italy, satellite Sentinel-2 data with support vector regression have been used to predict grape sugar content (Brix), improving harvest timing [81,69] . For orchards, one case in India used UAV RGB imaging of mango orchards processed by a YOLO object detector to count flowering clusters, estimating fruit yield potential. Another in China employed hyperspectral imaging on a trolley in an apple orchard, an SVM model predicted fruit freshness and quality factors during harvesting [70] .

Tree Crops: In the U.S., almond growers use aerial LiDAR to measure canopy volume, correlated by linear regression with expected nut yield. In Australia, Sentinel-1 SAR data with a CNN model classified pistachio orchards by tree health status, aiding irrigation managementn [71] .

Root/Tuber crops: Drone NDVI imagery of potato fields in the U.K. analyzed by random forests has helped forecast tuber yield before harvest. In potato late blight outbreak areas, thermal imaging combined with CNN detection models identified infection hotspots [72] .

Conclusion

Remote sensing and AI-driven technologies are rapidly transforming contemporary agriculture and horticulture. This review has chronicled their historical roots, examined current methods and platforms and showcased diverse applications for crop improvement around the world. By marrying detailed environmental sensing with powerful analytics, farmers and stakeholders can gain actionable insights at a scale and precision previously unimaginable. Remote sensing supplies comprehensive data on crop condition, soil and environment, AI converts this data into understandinghighlighting stress, predicting yield and guiding interventions. The evidence suggests substantial benefits: higher yields, better resource efficiency and quicker response to threats in both field crops and high-value horticulture. Yet challenges remain: technical (data limitations, algorithm biases), practical (costs, skills) and policyoriented (data governance, infrastructure). Addressing these through interdisciplinary research and informed policy will be key. The four tables provided in this article systematically summarize the technologies (Table 1), AI models (Table 2), real-world cases (Table 3) and challenges with mitigations (Table 4), equipping readers with a structured overview. Looking ahead, the synergy of remote sensing and AI promises a new era of digital farmingdata-driven, precise and adaptable. Emerging trends like hyper-resolution imaging, edge computing and autonomous systems suggest that within the next decade, many routine farm decisions will be aided or automated by intelligent systems. This has profound implications for food security: as global population grows and climate pressures mount, these technologies will be indispensable for increasing productivity sustainably. In conclusion, remote sensing and AI are not merely tools but enablers of a paradigm shift in how we cultivate and manage crops. They represent a technological revolution that, if carefully deployed and widely accessible, can significantly improve agricultural outcomes. Continued innovation, coupled with attention to equity and ethics, will ensure that the full potential of these advances benefits farmers, consumers and the environment alike. The future of crop

References

1. Khonina SN, Kazanskiy NL, Oseledets IV, Nikonorov AV, Butt MA. Synergy between artificial intelligence and hyperspectral imagining-a review. Technologies. 2024;12:163.
2. Chamasemani FF, Singh YP. Multi-class support vector machine (SVM) classifiers-an application in hypothyroid detection and classification. In: Proceedings of the Sixth International Conference on Bio-Inspired Computing: Theories and Applications; 2011 Sep 27-29; Penang, Malaysia. p. 351-356.
3. Zhang L, Zhang L. Artificial intelligence for remote sensing data analysis: a review of challenges and opportunities. IEEE Geoscience and Remote Sensing Magazine. 2022;10:270-294.
4. Fabbri AG, Fung KB, Yatabe SM. The usage of artificial intelligence in remote sensing: a review of applications and current research. In: Chung CF, Fabbri AG, editors. Quantitative analysis of mineral and energy resources. Dordrecht: Springer; 1988. p. 489-512.
5. Sharifi A, Mahdipour H. Utilizing geospatial artificial intelligence for remote sensing applications. Environmental Earth Sciences. 2024;183:274.
6. Zhao T, Wang S, Ouyang C, Chen M, Liu C, Zhang J, et al. Artificial intelligence for geoscience: progress, challenges and perspectives. The Innovation. 2024;5:100691.
7. Abdelmajeed AYA, Juszczak R. Challenges and limitations of remote sensing applications in northern peatlands: present and future prospects. Remote Sensing. 2024;16:591.
8. Aragoneses E, García M, Ruiz-Benito P, Chuvieco E. Mapping forest canopy fuel parameters at European scale using spaceborne LiDAR and satellite data. Remote Sensing of Environment. 2024;303:114005.
9. Cremons DR. The future of LiDAR in planetary science. Frontiers in Remote Sensing. 2022;3:1042460.
10. Debnath S, Paul M, Debnath T. Applications of LiDAR in agriculture and future research directions. Journal of Imaging. 2023;9:57.
11. Disney M. Terrestrial LiDAR: a three-dimensional revolution in how we look at trees. New Phytologist. 2019;222:1736-1741.
12. Prajval V, Krishnamoorthi A, Thakur R, Ruchitha T, Kapoor M, Singh A, et al. From code to crop: how bioinformatics is transforming crop genomics in modern agriculture and bettering environment. Journal of Advances in Biology and Biotechnology. 2024;27(4):27-49.
13. Singh A, Labanya GSR. Exploring the role of hydrogen in agriculture for machinery, biomass and reducing carbon footprints. Plant Archives. 2025;25(1):2852-2863.
14. Debnath P, Raj R. Optimizing functional genomics and application of root wounding and immersion for enhanced virus-induced gene silencing in plants: a comprehensive review. Plant Archives. 2025;25(1):3115-3126.
15. Krishnamoorthi A, Chaurasia J, Baidya BK, Singh A, Kumar V, Singh A. A comprehensive review on evolution, challenges of models, opportunities in urban farming practices in the world. Journal of Scientific Research and Reports. 2024;30(6):136-156.
16. Raghuvanshi HR, Kalaiselvi P, Ravindra NR, Kumar V. Biotechnological breakthroughs: paving the path to cleaner and more productive agriculture through bioremediation. Journal of Advances in Biology and Biotechnology. 2024;27(4):119-142.
17. Bhardwaj R, Kumar M, Kaushal N, Kamboj AD, Krishnamoorthi A, Singh A, et al. From lab to bouquet: the biotechnological frontier in modern floriculture for sustainable and resilient flower farming. Journal of Advances in Biology and Biotechnology. 2024;27(2):119137.
18. Jain S, Ranganna G, Jadhav PS, Shrivastava U, Sood A, Prasad L, et al. Cultivating tomorrow: harnessing gene editing and silencing for precision horticulture. Journal of Advances in Biology and Biotechnology. 2024;27(1):147160.
19. Krishnamoorthi A, Salam NK, Kalaiselvi D, KB C, Kumar S, Kumar V, et al. Digital sequencing information in agricultural crops: a comprehensive review. International Journal. 2024;8(8):1404-1412.
20. Rimpika, Anushi, Manasa S, Anusha KN, Sharma S, Thakur A, et al. An overview of precision farming. International Journal of Environment and Climate Change. 2023;13(12):441-456.
21. Jain S, Bhujel S, Shrivastava U, Mohapatra A, Mishra G. Advancements in drone technology for fruit crop management: a comprehensive review. 2023.
22. Jaboyedoff M, Oppikofer T, Abellan A, Derron MH, Loye A, Metzger R, et al. Use of LiDAR in landslide investigations: a review. Natural Hazards. 2012;61:528.
23. Zhao Q, Qu Y. The retrieval of ground NDVI (normalized difference vegetation index) data consistent with remotesensing observations. Remote Sensing. 2024;16:1212.
24. Mitchell AL, Rosenqvist A, Mora B. Current remote sensing approaches to monitoring forest degradation in support of countries measurement, reporting and verification (MRV) systems for REDD+. Carbon Balance and Management. 2017;12:9.
25. Chen Y, Morton DC, Randerson JT. Remote sensing for wildfire monitoring: insights into burned area, emissions and fire dynamics. One Earth. 2025;7:1022-1028.
26. Pandey P, Ramanathan A, Venkataraman G. Remote sensing of mountain glaciers and related hazards. In: Marghany M, editor. Environmental applications of remote sensing. Rijeka: IntechOpen; 2016.
27. Anushi BPS, Sachan K. Bioformulation: a new frontier in horticulture for eco-friendly crop management. Journal of Plant Biota. 2024.
28. Garg S, Dasgupta A, Motagh M, Martinis S, Selvakumaran S. Unlocking the full potential of Sentinel-1 for flood detection in arid regions. Remote Sensing of Environment. 2025;315:114417.
29. Nguyen-Kim S, Nguyen-The V, Nguyen DB. A systematic review of artificial intelligence in geographic information systems. In: Nghia PT, Thai VD, Thuy NT, Son LH, Huynh VN, editors. Advances in information and communication technology. Cham: Springer; 2023. p. 20-31.
30. Anjana NS, Amarnath A, Harindranathan Nair MV. Toxic hazards of ammonia release and population vulnerability assessment using geographical information system. Journal of Environmental Management. 2018;210:201-209.
31. Xia N, Cheng L, Li M. Mapping urban areas using a combination of remote sensing and geolocation data. Remote Sensing. 2019;11:1470.
32. Furberg D, Ban Y, Mortberg U. Monitoring urban green infrastructure changes and impact on habitat connectivity using high-resolution satellite data. Remote Sensing. 2020;12:3072.
33. Akhyar A, Asyraf Zulkifley M, Lee J, Song T, Han J, Cho C, et al. Deep artificial intelligence applications for natural disaster management systems: a methodological review. Ecological Indicators. 2024;163:112067.
34. Gu Z, Zeng M. The use of artificial intelligence and satellite remote sensing in land cover change detection: review and perspectives. Sustainability. 2024;16:274.
35. Anushi AK, Ghosh PK. From seed to succulence: mastering dragon fruit propagation techniques. Journal of Plant Biota. 2024.
36. Xuan X, Jianbo L, Jin Y. Research on the natural language querying for remote sensing databases. In: Proceedings of the International Conference on Computer Science and Service System; 2012 Aug 11-13; Nanjing, China. p. 228231.
37. Bashmal L, Bazi Y, Melgani F, Al Rahhal MM, Al Zuair MA. Language integration in remote sensing: tasks, datasets and future directions. IEEE Geoscience and Remote Sensing Magazine. 2023;11:63-93.
38. Tounsi A, Temimi M. A systematic review of natural language processing applications for hydrometeorological hazards assessment. Natural Hazards. 2023;116:2819-2870.
39. Wu X, Hong D, Chanussot J. Convolutional neural networks for multimodal remote sensing data classification. IEEE Transactions on Geoscience and Remote Sensing. 2022;60:5517010.
40. Qiang W, Zhongli Z. Reinforcement learning model, algorithms and its application. In: Proceedings of the International Conference on Mechatronic Science, Electric Engineering and Computer; 2011 Aug 19-22; Jilin, China. p. 1143-1146.
41. Song Y, Kalacska M, Gasparovic M, Yao J, Najibi N. Advances in geocomputation and geospatial artificial intelligence (GeoAI) for mapping. International Journal of Applied Earth Observation and Geoinformation. 2023;120:103300.
42. Ghosh B, Garg S, Motagh M. Automatic flood detection from Sentinel-1 data using deep learning architectures. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2022;V-3-2022:201-208.
43. WIRED. Early detection can't stop every wildfire. 2025.
44. Reuters. Field to cloud: how AI is helping regenerative agriculture grow. 2024.
45. The Associated Press. Artificial intelligence helps track spider monkeys. 2025.
46. Shmilovici A. Support vector machines. In: Maimon O, Rokach L, editors. Data mining and knowledge discovery handbook. Boston: Springer; 2009. p. 231-247.
47. Jun Z. The development and application of support vector machine. Journal of Physics: Conference Series. 2021;1748:052006.
48. Guido R, Ferrisi S, Lofaro D, Conforti D. An overview on the advancements of support vector machine models in healthcare applications: a review. Information. 2024;15:235.
49. Ghosh S, Dasgupta A, Swetapadma A. A study on support vector machine based linear and non-linear pattern classification. In: Proceedings of the International Conference on Intelligent Sustainable Systems; 2019 Feb 21-22; Palladam, India. p. 24-28.
50. Sheykhmousa M, Mahdianpari M, Ghanbari H, Mohammadimanesh F, Ghamisi P, Homayouni S. Support vector machine versus random forest for remote sensing image classification: a meta-analysis and systematic review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020;13:6308-6325.
51. Gaye B, Zhang D, Wulamu A. Improvement of support vector machine algorithm in big data background. Mathematical Problems in Engineering. 2021;2021:5594899.
52. Amaya-Tejera N, Gamarra M, Velez JI, Zurek E. A distance-based kernel for classification via support vector machines. Frontiers in Artificial Intelligence. 2024;7:1287875.
53. Evgeniou T, Pontil M. Support vector machines: theory and applications. In: Paliouras G, Karkaletsis V, Spyropoulos CD, editors. Machine learning and its applications: advanced lectures. Berlin: Springer; 2001. p. 249-257.
54. Yang Q. Research on SVM remote sensing image classification based on parallelization. Journal of Physics: Conference Series. 2021;1852:032009.
55. Salleh SA, Khalid N, Danny N, Zaki NAM, Ustuner M, Latif ZA, et al. Support vector machine (SVM) and object based classification in earth linear features extraction: a comparison. Revue Internationale de Géomatique. 2024;33:183-199.
56. Liu Y, Wang Y, Zhang J. New machine learning algorithm: random forest. In: Liu B, Ma M, Chang J, editors. Information computing and applications. Berlin: Springer; 2012. p. 246-252.
57. Sun Z, Wang G, Li P, Wang H, Zhang M, Liang X. An improved random forest based on the classification accuracy and correlation measurement of decision trees. Expert Systems with Applications. 2024;237:121549.
58. Sipper M, Moore JH. Conservation machine learning: a case study of random forests. Scientific Reports. 2021;11:3629.
59. Tang J, Henderson A, Gardner P. Exploring AdaBoost and random forests machine learning approaches for infrared pathology on unbalanced data sets. Analyst. 2021;146:58805891.
60. Vergni L, Todisco F. A random forest machine learning approach for the identification and quantification of erosive events. Water. 2023;15:2225.
61. Joelsson SR, Benediktsson JA, Sveinsson JR. Random forest classification of remote sensing data. In: Chen CH, editor. Signal and image processing for remote sensing. Boca Raton: CRC Press; 2006. p. 327-344.
62. Gislason PO, Benediktsson JA, Sveinsson JR. Random forest classification of multisource remote sensing and geographic data. In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium; 2004 Sep 2024;
63. Georganos S, Grippa T, Niang Gadiaga A, Linard C, Lennert M, Vanhuysse S, et al. Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling. Geocarto International. 2019;36:121136.
64. Ezugwu AE, Ikotun AM, Oyelade OO, Abualigah L, Agushaka JO, Eke CI, et al. A comprehensive survey of clustering algorithms: state-of-the-art machine learning applications, taxonomy, challenges and future research prospects. Engineering Applications of Artificial Intelligence. 2022;110:104743.
65. Bhagwat RU, Uma Shankar B. A novel multilabel classification of remote sensing images using XGBoost. In: Proceedings of the IEEE 5th International Conference for Convergence in Technology; 2019 Mar 29-31; Bombay, India. p. 1-5.
66. Militino AF, Goyena H, Perez-Goya U, Ugarte MD. Logistic regression versus XGBoost for detecting burned areas using satellite images. Environmental and Ecological Statistics. 2024;31:57-77.
67. Liu Y, Wu S, Wu Z, Zhou S. Application of gradient boosting machine in satellite-derived bathymetry using Sentinel-2 data for accurate water depth estimation in coastal environments. Journal of Sea Research. 2024;201:102538.
68. McCarty DA, Kim HW, Lee HK. Evaluation of light gradient boosted machine learning technique in large scale land use and land cover classification. Environments. 2020;7:84.
69. Bui QT, Chou TY, Hoang TV, Fang YM, Mu CY, Huang PH, et al. Gradient boosting machine and object-based CNN for land cover classification. Remote Sensing. 2021;13:2709.
70. Shao Z, Ahmad MN, Javed A. Comparison of random forest and XGBoost classifiers using integrated optical and SAR features for mapping urban impervious surface. Remote Sensing. 2024;16:665.
71. Kumar DG, Chaudhari S. AUXG: deep feature extraction and classification of remote sensing image scene using attention UNet and XGBoost. Journal of the Indian Society of Remote Sensing. 2024;52:1687-1698.
72. Belgiu M, Dragut L. Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. 2016;114:24-31.
73. Hassine K, Erbad A, Hamila R. Important complexity reduction of random forest in multi-classification problem. In: Proceedings of the International Wireless Communications and Mobile Computing Conference; 2019 Jun 24-28;
74. Lee WM. Supervised learning-classification using Knearest neighbors (KNN). In: Lee WM, editor. Python machine learning. Hoboken: John Wiley and Sons; 2019. p. 205-220.
75. Zaky D, Gunawan PH. Computational parallel of K-nearest neighbor on page blocks classification dataset. In: Proceedings of the International Conference on Information and Communication Technology; 2020 Jun 24-26;
76. Ray S. An analysis of computational complexity and accuracy of two supervised machine learning algorithmsK-nearest neighbor and support vector machine. In: Sharma N, Chakrabarti A, Balas V, Martinovic J, editors. Data management, analytics and innovation. Singapore: Springer; 2020. p. 335-347.
77. Rodriguez MZ, Comin CH, Casanova D, Bruno OM, Amancio DR, Costa LDF, et al. Clustering algorithms: a comparative approach. PLoS ONE. 2019;14:e0210236.
78. Li H, Liu X, Li T, Gan R. A novel density-based clustering algorithm using nearest neighbor graph. Pattern Recognition. 2020;102:107206.
79. Ahmed Soomro A, Akmar Mokhtar A, Hussin HB, Lashari N, Lekan Oladosu T, Muslim Jameel S, et al. Analysis of machine learning models and data sources to forecast burst pressure of petroleum corroded pipelines: a comprehensive review. Engineering Failure Analysis. 2024;155:107747.