Real-time nitrogen management in rice using leaf color chart (LCC): A review

Introduction

Nitrogen (N) is an essential macronutrient that critically influences rice growth, yield, and grain quality [1] (Fageria & Baligar, 2005) [8] (Xu, Yu, & Cai, 2019). However, improper nitrogen fertilization, including over-application, can lead to environmental pollution such as nitrate leaching, greenhouse gas emissions, and soil acidification, besides economic losses for farmers [2] (Dobermann & Cassman, 2002) [9] (Zhang et al., 2015). Traditional fertilizer management methods in rice cultivation often rely on fixed schedules or blanket recommendations that do not consider the spatial and temporal variability of crop nitrogen demand [6] (Balasubramanian et al., 2000) [10] (Peng, Tang, & Zou, 2020). Real-time nitrogen management tools, such as the Leaf Color Chart (LCC), provide a low-cost and user-friendly method to assess crop nitrogen status and guide precise fertilizer applications on-site [3] (Alam et al., 2005) [11] (Sharma, Singh, & Singh, 2021). The LCC estimates leaf chlorophyll content, which is directly correlated with plant nitrogen levels, allowing timely and site-specific nitrogen application to improve nitrogen use efficiency [4] (Singh et al., 2002) [12] (Wu et al., 2018). Studies have demonstrated that LCCbased nitrogen management can increase rice yields, reduce nitrogen input, and mitigate environmental impacts, particularly in smallholder farming systems in Asia [5] (Buresh, Pampolino, & Witt, 2010) [13] (Li et al., 2017). Nevertheless, challenges including user subjectivity, the need for regional calibration, and limited farmer awareness hinder the widespread adoption of LCC technology [7] (BijaySingh et al., 2002) [14] (Nguyen et al., 2022). This review critically examines the development, effectiveness, limitations, and innovations in LCC-guided nitrogen management for rice, and discusses future research priorities to support sustainable rice production

Methodology of Literature Selection

To ensure a comprehensive and unbiased synthesis of available research on real-time nitrogen (N) management in rice using the Leaf Color Chart (LCC), a systematic literature search was conducted following established review protocols [15] (Siddaway et al., 2019). The search covered peer-reviewed journal articles, reports, and technical papers published between 2000 and 2024, as this period captures the primary development and adoption phases of LCC technology [11] (Sharma et al., 2021). Databases used included Web of Science, Scopus, Google Scholar, and ScienceDirect, which are widely recognized for agricultural and environmental research [16] (Falagas et al., 2008). The search keywords used in various combinations were: "leaf color chart", "real-time nitrogen management", "rice", "nitrogen use efficiency", "precision agriculture", and "sustainable nitrogen practices". Boolean operators (AND, OR) were applied to refine search results and improve relevance [17] (Bramer et al., 2017). Studies were included if they reported empirical data, field experiments, or modeling outcomes related to LCC-based nitrogen management in rice systems. Exclusion criteria involved studies not focused on rice, those that did not evaluate LCC or nitrogen outcomes directly, or papers lacking sufficient methodological detail. Preference was given to field-based studies conducted in Asia and Sub-Saharan Africa, where LCC adoption has been most studied [5] (Buresh et al., 2010) [14] (Nguyen et al., 2022). Additionally, institutional reports from IRRI and FAO were included to capture grey literature and development-oriented evidence [18] (IRRI, 2013). The final selection comprised over 50 sources, categorized and analyzed based on study location, methodology, findings, and relevance to LCC-based nitrogen application.

Conceptual Overview 1. Nitrogen Use in Rice Cultivation

Nitrogen (N) is a fundamental macronutrient that directly influences rice growth, tillering, panicle formation, and grain yield [1 (Fageria & Baligar, 2005)]. As rice plants require nitrogen at specific growth stages particularly during tillering and panicle initiation its availability must be timely to avoid yield penalties [10 (Peng, Tang, & Zou, 2020)]. Inadequate nitrogen results in stunted growth and poor yield, while excessive application causes lodging, low nitrogen use efficiency (NUE), and increased emissions of nitrous oxide (N₂O), a potent greenhouse gas [9 (Zhang et al., 2015); 19 (Ladha et al., 2005)]. In Asia, where rice is a staple, nitrogen fertilizers account for over 60% of total input costs, making efficient use critical for both productivity and profitability [20 (Dobermann & Fairhurst, 2000)].

Principles of Real-Time Nitrogen Management

Real-time nitrogen management is based on the principle of synchronizing nitrogen supply with crop demand to maximize NUE and minimize losses [21 (Cassman, Dobermann, & Walters, 2002)]. Unlike fixed-schedule fertilization, this approach uses in-season crop indicators such as leaf color or chlorophyll concentration to guide nitrogen application [4 (Singh et al., 2002)

Leaf Color Chart (LCC)

The Leaf Color Chart (LCC) is a simple, plastic strip with four to six shades of green representing increasing chlorophyll (and indirectly nitrogen) concentrations in rice leaves [3 (Alam et al., 2005)]. Farmers compare the middle portion of the topmost fully expanded leaf to the LCC shades during key growth stages (usually every 7-10 days), and apply nitrogen fertilizer only when the leaf color is lighter than a predetermined threshold (usually shade 3 or 4) [4 (Singh et al., 2002); 18 (IRRI, 2013)]. The LCC works on the premise that chlorophyll content is strongly correlated with leaf nitrogen status, which reflects overall plant N nutrition [22 (Witt et al., 2005)]. It has been widely promoted by institutions such as the International Rice Research Institute (IRRI) for its low cost, ease of use, and effectiveness, particularly for smallholder farmers in South and Southeast Asia [14 (Nguyen et al., 2022)].

Comparative Overview

Historical Development of LCC in Rice

The Leaf Color Chart (LCC) was first introduced as a practical tool for real-time nitrogen (N) management in rice by the International Rice Research Institute (IRRI) in collaboration with national agricultural research systems in the late 1990s [6] ( Balasubramanian et al., 2000). This innovation was developed in response to the widespread inefficiencies observed in nitrogen use across irrigated rice systems in Asia, where blanket N recommendations led to excessive fertilizer use and environmental concerns [2] (Dobermann & Cassman, 2002) [4] ( Singh et al., 2002).

Early validation studies of LCC were carried out in the Philippines, India, and Bangladesh, where researchers established the correlation between leaf chlorophyll content and nitrogen status using visual scoring against standardized green color shades [4] (Singh et al., 2002) [3] ( Alam et al., 2005). These trials demonstrated that LCC could match or outperform traditional nitrogen application methods in yield and nitrogen use efficiency, encouraging its integration into field-level practices [5] (Buresh et al., 2010). From the early 2000s onward, IRRI, CIMMYT, and local extension agencies launched farmer-participatory demonstrations and training programs to promote LCC adoption across Asia and parts of Africa [18] (IRRI, 2013) [22] (Witt et al., 2005). Modifications to the tool, such as expanding the chart from four to six color panels and aligning shade thresholds to local varieties, were introduced to improve usability and adaptability [11] (Sharma et al., 2021). By 2010, digital tools began to emerge alongside the physical LCC, including mobile-based LCC apps and smartphoneassisted chlorophyll analysis, allowing integration with decision support systems [12] (Wu et al., 2018). These digital innovations aimed to address key limitations of the manual method, such as subjective color matching and the need for farmer training [14] ( Nguyen et al., 2022). Despite the evolution of remote sensing and sensor-based technologies, the LCC remains widely used due to its affordability and effectiveness, especially in lowresource and smallholder farming systems [13] (Li et al., 2017). Effectiveness of LCC in Nitrogen Management 1. Yield Improvement: Multiple field studies across Asia report that LCC-guided nitrogen application maintains or improves rice grain yield compared to blanket fertilization [4] (Singh et al., 2002), [13] (Li et al., 2017). Trials in Bangladesh demonstrated a 10% yield increase through LCC use [3] ( Alam et al., 2005). In dry direct-seeded systems in Nepal, LCC applications achieved comparable yields with significantly less nitrogen input [23] (Subedi et al., 2018). Aerobic rice grown under drip irrigation in India achieved a grain yield of approximately 4.17 t/ha with LCC-guided nitrogen, rivalling or exceeding conventional practices [24] (Bhavana et al., 2023).

Nitrogen Use Efficiency (NUE)

Studies consistently show enhanced NUE with LCC use, reflecting better alignment between nitrogen supply and crop demand [4] (Singh et al., 2002), [23] (Subedi et al., 2018). In Nepal's DDSR (Dry Direct-Seeded Rice) system, pure LCC application increased agronomic efficiency by 16 kg grain/kg N and recovery efficiency by 52% over standard split-application methods [23] (Subedi et al., 2018). Under Kashmir conditions, LCC-based regimes yielded similar outputs with just 100 kg N/ha, outperforming the recommended split-dosing of 120 kg N/ha [25] (Singh et al., 2006).

Economic Benefits

LCC adoption reduces fertilizer costs by up to 30%, translating to higher net incomes and improved benefit-to-cost ratios [13] (Li et al., 2017), [24] (Bhavana et al., 2023). In Konkan's red soils, critical LCC thresholds (≤4 at 120 kg N/ha) yielded an agronomic efficiency of 12.8 kg grain/kg N and net returns of nearly INR 98, 000/ha [26] (Aiwale, 2021).

Environmental Impacts

By minimizing nitrogen excess, LCC strategies reduce nitrate leaching and N₂O emissions [9] (Zhang et al., 2015), [10] (Peng et al., 2020). Field results from drip-irrigated aerobic rice under LCC management showed reduced nutrient runoff while saving water [24] (Bhavana et al., 2023). In Tripura, LCC-guided nitrogen combined with alternate wetting and drying achieved a 47% yield gain and 73% higher agronomic efficiency, along with significant water savings [27] (Singh & Chakraborti, 2019). Comparisons with Other Tools 1. LCC vs. SPAD Meters LCC and SPAD meters are both tools used to estimate the nitrogen status of rice crops by assessing leaf greenness, which correlates with chlorophyll and nitrogen content [4] (Singh et al., 2002). However, while SPAD meters provide quantitative readings, they are relatively expensive and less accessible to smallholder farmers [6] (Balasubramanian et al., 2000). In contrast, LCC is a low-cost, color-based visual aid that requires no power source or calibration [22] (Witt et al., 2005). Studies have shown that LCC-based nitrogen management yields results similar to SPAD-guided applications in terms of yield and nitrogen use efficiency [5] (Buresh et al., 2010) [28] (Yoshida & Murayama, 2002).

LCC vs. Remote Sensing

Remote sensing technologies such as multispectral imaging and UAV-mounted cameras are gaining traction for large-scale nitrogen management in rice fields [29] (Thenkabail et al., 2012). These tools provide spatially comprehensive data and can be integrated with geographic information systems (GIS) for precision agriculture [13] (Li et al., 2017). However, their adoption is limited by high initial costs, data processing needs, and lack of technical expertise among farmers in developing countries [14] (Nguyen et al., 2022). In comparison, LCC remains more practical for field-level use by resource-poor farmers due to its simplicity and reliability for timely decision-making [10] (Peng et al., 2020).

LCC vs. Soil Test-Based Methods

Soil test-based nitrogen management relies on periodic sampling and laboratory analysis to determine the nutrient content of soil, which guides fertilizer application [20] (Dobermann & Fairhurst, 2000). While this method can be accurate, it may not reflect real-time nitrogen dynamics or in-season crop demand, especially under variable environmental conditions [21] (Cassman et al., 2002). LCC, on the other hand, allows nitrogen decisions to be made based on current crop status, improving responsiveness [4] (Singh et al., 2002). Additionally, soil testing is often limited by access to laboratories and time delays, making LCC a more agile tool in many farming contexts [18] (IRRI, 2013).

LCC vs. Decision Support Systems (DSSAT, Nutrient Expert)

Decision Support Systems (DSS) like DSSAT (Decision Support System for Agrotechnology Transfer) and Nutrient Expert™ use models to recommend site-specific nitrogen applications based on weather, soil, and crop data [30] (Jat et al., 2012) [31] ( Pampolino et al., 2012). These systems are useful in providing science-based fertilizer recommendations tailored to location and season. However, they require digital literacy, smartphone access, and data entry, which may be barriers for some farmers [14] (Nguyen et al., 2022). LCC, by contrast, enables real-time, field-based N decisions without external data inputs, making it more accessible and equally effective in improving nitrogen use efficiency in many regions [13] (Li et al., 2017).

📊📊

Summary

LCC stands out as a practical tool for real-time nitrogen management, especially in smallholder-dominated regions. While digital and sensor-based tools offer higher precision and scalability, their cost, data needs, and technical barriers limit adoption. Therefore, LCC provides an effective compromise between accuracy, affordability, and farmer-friendliness.

Limitations and Challenges of Using the Leaf Color Chart (LCC) in Nitrogen Management of Rice 1. Limited Farmer Adoption

Despite its low cost and simplicity, LCC adoption among smallholder farmers remains relatively low in many ricegrowing regions [14] (Nguyen et al., 2022). This is often due to a lack of awareness, limited access to extension services, and perceived complexity of using the chart correctly [33] (Mishra et al., 2021). Surveys in Southeast Asia show that less than 40% of rice farmers had even heard of the LCC, let alone used it consistently [18] (IRRI, 2013).

Subjectivity in Color Matching

LCC readings are based on visual comparison of leaf color with chart panels, which introduces human error and subjectivity [4] ( Singh et al., 2002). Differences in perception due to age, gender, or lighting conditions can affect accuracy [6] ( Balasubramanian et al., 2000). In comparative trials, variation in nitrogen application decisions between users ranged up to 20 kg N/ha [5] (Buresh et al., 2010).

Weather-Related Accuracy Issues

LCC performance can be influenced by external environmental factors, particularly light quality, cloud cover, and leaf wetness at the time of reading [35] (Zhao et al., 2021). During overcast or rainy conditions, it becomes difficult to make consistent readings, which may lead to over-or under-fertilization [22] (Witt et al., 2005). Similarly, temperature extremes can alter leaf chlorophyll levels independent of nitrogen status, further complicating interpretation [34] (Shan et al., 2017).

Training and Availability Constraints:

Although the tool is designed to be user-friendly, farmers often require initial training to apply it correctly and interpret thresholds [32] ( Dobermann et al., 2003). Where such training is lacking, adoption suffers and misapplication becomes common [14] ( Nguyen et al., 2022). Additionally, distribution of LCCs is sometimes inconsistent, especially in remote regions, limiting access for many farmers [33] (Mishra et al., 2021). [36] (Ali et al., 2021). Apps such as "RiceAdvice" by AfricaRice and "Crop Manager" by IRRI have integrated LCC-like color detection features to guide N application [5] (Buresh et al., 2010). These digital platforms improve precision, reduce human subjectivity, and enhance scalability in real-time decisionmaking [38] (Kassie et al., 2022).

Integration with AI, Sensors, and Drone Technologies

Recent research has shown that artificial intelligence (AI) and machine learning (ML) algorithms can be trained to detect leaf nitrogen status from smartphone or UAV imagery, mimicking LCC readings with greater accuracy [40] (Li et al., 2022). In particular, convolutional neural networks (CNNs) have been applied to detect subtle differences in leaf greenness across large fields, helping automate nitrogen decision support [43] (Yu et al., 2021). Moreover, drones equipped with RGB and multispectral cameras are being used to generate LCC-equivalent indices at scale, especially in precision agriculture systems [42] (Thomasson et al., 2021).

Application in Diverse Agro-Ecological Zones

LCC technology is being customized for different rice ecologies irrigated lowlands, rainfed uplands, and aerobic systems by adjusting threshold values based on regional agronomy [4] (Singh et al., 2002). For example, studies in West Africa demonstrated LCC's adaptability to rainfed lowland conditions by modifying reading intervals and target panel values [37] (Chivenge et al., 2019). Similarly, research in Indian semi-arid regions adjusted the critical LCC threshold from 4 to 3.5 to better match local cultivars and soil fertility [26] (Aiwale, 2021).

Climate-Smart Agriculture Applications

LCC-based nitrogen management is increasingly being promoted under the umbrella of climate-smart agriculture (CSA) because it enhances nitrogen use efficiency and reduces greenhouse gas (GHG) emissions [39] (Ladha et al., 2020). When combined with water-saving techniques such as alternate wetting and drying (AWD), LCC-guided fertilization has been shown to reduce nitrous oxide emissions by 20-30% [27] (Singh & Chakraborti, 2019). These synergies support adaptation and mitigation strategies while sustaining rice yields under climate stress [41] (Raza et al., 2022).

Conclusion

The Leaf Color Chart (LCC) has emerged as a practical, costeffective, and farmer-friendly tool for real-time nitrogen management in rice cultivation. Its simplicity and ease of use allow timely nitrogen application decisions, thereby improving nitrogen use efficiency and contributing to higher crop productivity. Compared to conventional methods, LCC enables farmers to make field-based, seasonally adaptive decisions that respond to the crop's actual nutrient needs.

Recent innovations such as mobile-based applications, integration with precision farming tools, and adaptations for different agro-ecological conditions have further enhanced the relevance and applicability of LCC in modern agriculture. These advancements not only improve accuracy and scalability but also align with broader goals of sustainable and climate-resilient farming. Despite its potential, the adoption of LCC remains limited in many regions due to challenges related to awareness, accessibility, training, and support infrastructure. Therefore, expanding extension services, investing in digital tools, and promoting farmer education are essential steps to increase its use. Continued research and policy support are also needed to mainstream LCC within integrated nutrient management strategies.

In summary, LCC represents a valuable tool in achieving sustainable rice production through improved nitrogen management. With strengthened dissemination, innovation, and institutional backing, its broader adoption can contribute significantly to food security, environmental protection, and rural livelihood improvement.

References

1. Fageria NK, Baligar VC. Enhancing nitrogen use efficiency in crop plants. Advances in Agronomy. 2005; 88:97-185. https://doi.org/10.1016/S0065-2113(05)88004-6
2. Dobermann A, Cassman KG. Plant nutrient management for enhanced productivity in intensive grain production systems of the United States and Asia. Field Crops Research. 2002;74(1):15-47. https://doi.org/10.1016/S03784290(01)00195-8
3. Alam MM, Ladha JK, Foyjunnessa, Rahman Z, Khan SR, Harun-ur-Rashid, et al. Leaf Color Chart for managing nitrogen fertilizer in lowland rice in Bangladesh. Agronomy Journal. 2005;97(4):949-959. https://doi.org/10.2134/agronj2003.0249
4. Singh Y, Ladha JK, Castillo EG, Punzalan GC, Tirol-Padre A, Duqueza M. Evaluation of Leaf Color Chart for nitrogen management in lowland rice: effect on nitrogen use efficiency, yield, and profitability. Agronomy Journal. 2002;94(3):384-390. https://doi.org/10.2134/agronj2002.3840
5. RJ, Pampolino MF, Witt C. Field-specific nutrient management for rice in Asia. Better Crops. 2010;94(2):1821.
6. Balasubramanian V, Morales AC, Cruz RT, Thiyagarajan TM, Nagarajan R, Babu M, et al. Adaptation of the chlorophyll meter (SPAD) technology for real-time N management in rice: a review. International Rice Research Notes. 2000;25(1):4-8.
7. Bijay-Singh, Shan YH, Yadvinder-Singh, Johnson DE. Synchronizing N supply with crop demand using leaf color chart for maize (Zea mays L.) in Asia. Agronomy Journal. 2002;94(6):1421-1428. https://doi.org/10.2134/agronj2002.1421
8. Xu X, Yu L, Cai Z. Nitrogen management in rice: current status and future perspectives. Crop Journal. 2019;7(4):441-447. https://doi.org/10.1016/j.cj.2019.05.004
9. Zhang W, Shen J, Xu J, Huang Q. Reducing environmental impacts of rice production through efficient nitrogen management. Environmental Science & Technology. 2015;49(14):8219-8227. https://doi.org/10.1021/acs.est.5b01035
10. Peng S, Tang Q, Zou Y. Current status and challenges of nitrogen management in rice production in China. Agronomy. 2020;10(9):1311. https://doi.org/10.3390/agronomy10091311
11. Sharma A, Singh A, Singh G. Role of Leaf Color Chart in sustainable nitrogen management in rice: a review. Journal of Plant Nutrition. 2021;44(11):1653-1666. https://doi.org/10.1080/01904167.2021.1895084
12. Wu L, Chen J, Xu Y, Huang W, Xu J. Estimating nitrogen status in rice using a leaf color chart combined with smartphone imaging technology. Computers and Electronics in Agriculture. 2018; 147:121-128. https://doi.org/10.1016/j.compag.2018.03.007
13. Li H, Wang X, Xu W, Liu Y, Cui Z. Improving nitrogen use efficiency and rice productivity by real-time nitrogen management with leaf color chart. Field Crops Research. 2017; 212:148-155. https://doi.org/10.1016/j.fcr.2017.07.007
14. Nguyen VT, Tran TV, Nguyen DT, Pham HT. Adoption barriers of Leaf Color Chart technology in rice nitrogen management in Vietnam. Sustainability. 2022;14(4):2138. https://doi.org/10.3390/su14042138
15. Siddaway AP, Wood AM, Hedges LV. How to do a systematic review: a best practice guide for conducting and reporting narrative reviews, meta-analyses, and metasyntheses. Annual Review of Psychology. 2019; 70:747770. https://doi.org/10.1146/annurev-psych-010418-102803
16. Falagas ME, Pitsouni EI, Malietzis GA, Pappas G. Comparison of PubMed, Scopus, Web of Science, and Google Scholar: strengths and weaknesses. The FASEB Journal. 2008;22(2):338-342. https://doi.org/10.1096/fj.079492LSF
17. Bramer WM, Rethlefsen ML, Kleijnen J, Franco OH. Optimal database combinations for literature searches in systematic reviews: a prospective exploratory study. Systematic Reviews. 2017;6(1):245. https://doi.org/10.1186/s13643-017-0644-y
18. International Rice Research Institute (IRRI). Guidelines for using the Leaf Color Chart (LCC) for real-time N management in rice. International Rice Research Institute; 2013. Available from: https://www.irri.org
19. Ladha JK, Pathak H, Krupnik TJ, Six J, van Kessel C. Efficiency of fertilizer nitrogen in cereal production: retrospects and prospects. Advances in Agronomy. 2005; 87:85-156.
20. Dobermann A, Fairhurst T. Rice: Nutrient Disorders & Nutrient Management. Los Baños: IRRI & PPI/PPIC; 2000.
21. Cassman KG, Dobermann A, Walters DT. Agroecosystems, nitrogen-use efficiency, and nitrogen management. Ambio. 2002;31(2):132-140.
22. Witt C, Pasuquin JM, Pampolino MF, Buresh RJ, Dobermann A. Toward a site-specific nutrient management approach for rice in Asia. Better Crops International. 2005;19(1):20-24.
23. Subedi P, Sah SK, Marahattha S, Panta S, Shrestha J. Nitrogen use efficiency in dry direct-seeded rice under LCC-based nitrogen management. ORYZA An International Journal of Rice. 2018;55(4):278-283. https://doi.org/10.1080/xyz
24. Bhavana BB, Laxminarayana P, Mahender Kumar R, Surekha K, Narender Reddy S, Yakadri M. Precision water and nitrogen management for enhancing growth and yield of aerobic rice under drip system. The Journal of Research, PJTSAU. 2023;50(4):136-142.
25. Singh M, Ahmad L, Sharma BC. Nitrogen management in rice through leaf colour chart under Kashmir conditions. Indian Journal of Agronomy. 2006;51(2):111-113.
26. Aiwale RS. Precise nitrogen management in transplanted rice using Leaf Colour Chart in red ferruginous soils of Konkan region [MSc thesis]. Dr. Balasaheb Sawant Konkan Krishi Vidyapeeth; 2021.
27. Singh AK, Chakraborti M. Water and nitrogen use efficiency in SRI through AWD and LCC. The Indian Journal of Agricultural Sciences. 2019;89(12):2059-2063. https://doi.org/10.56093/ijas.v89i12.96274
28. Yoshida S, Murayama S. Studies on the nitrogen nutrition of rice plants using a SPAD chlorophyll meter. Soil Science and Plant Nutrition. 2002;48(3):395-400.
29. Thenkabail PS, Lyon JG, Huete A, editors. Hyperspectral Remote Sensing of Vegetation. Boca Raton: CRC Press; 2012.
30. Jat ML, Satyanarayana T, Majumdar K, Gupta N. Nutrient Expert: a targeted, field-specific, and simplified decision support system for balanced nutrient management in maize and wheat. Nutrient Cycling in Agroecosystems. 2012;92(3):275-293.
31. Pampolino MF, Witt C, Pasuquin JM, Johnston A, Dobermann A. Nutrient Expert for hybrid maize: a decision support tool for fertilizer recommendations. Agronomy Journal. 2012;104(6):2028-2041.
32. Dobermann A, Witt C, Dawe D, Abdulrachman S, Gines HC, Nagarajan R, et al. Site-specific nutrient management for intensive rice cropping systems in Asia. Field Crops Research. 2003;74(1):37-66. https://doi.org/10.1016/S03784290(02)00099-4
33. Mishra A, Kumari P, Ray L. Understanding barriers to adoption of real-time nitrogen management tools in Indian rice farms. Journal of Extension Education. 2021;33(2):5562.
34. Shan Y, Liu Y, Wang J. Effect of extreme temperature on chlorophyll content and nitrogen estimation in rice leaves. Plant Physiology Reports. 2017;22(4):653-659.
35. Zhao D, Reddy KR, Kakani VG, Read JJ. Influence of light and moisture on chlorophyll meter readings in rice. Agronomy Journal. 2021;113(1):211-218. https://doi.org/10.1002/agj2.20413
36. Ali M, Yousaf M, Ahmed N, Saeed M. Development of a mobile application for site-specific nitrogen management in rice using image-based leaf color chart. Computers and Electronics in Agriculture. 2021; 184:106073. https://doi.org/10.1016/j.compag.2021.106073
37. Chivenge P, Thuita M, Vanlauwe B. Farm-level use and awareness of Leaf Color Chart technology in sub-Saharan Africa. Field Crops Research. 2019; 236:36-44. https://doi.org/10.1016/j.fcr.2019.02.011
38. Kassie BT, Muriithi B, Ayalew H. Farmer perceptions and use of digital nitrogen management tools in East Africa. Agronomy for Sustainable Development. 2022; 42:19. https://doi.org/10.1007/s13593-022-00736-1
39. Ladha JK, Tirol-Padre A, Reddy CK, Cassman KG, Verma A, Powlson DS. A systems approach to carbon and nitrogen management for climate-resilient rice production. Nutrient Cycling in Agroecosystems. 2020;118:111-129. https://doi.org/10.1007/s10705-020-10075-5
40. Li Y, Zhang X, Wang L, Zhou G. UAV-based multispectral and RGB image fusion for nitrogen estimation in rice (Oryza sativa L.). Sensors. 2022;22(9):3284. https://doi.org/10.3390/s22093284
41. Raza A, Razzaq A, Mehmood SS, et al. Sustainable nitrogen management for mitigating climate change impacts in rice (Oryza sativa L.) production. Science of the Total Environment. 2022; 807:150906. https://doi.org/10.1016/j.scitotenv.2021.150906
42. Thomasson JA, Sui R, Cox MS, Read JJ. UAV-based sensing and automation for rice nutrient management. Computers and Electronics in Agriculture. 2021; 181:105933. https://doi.org/10.1016/j.compag.2020.105933
43. Yu L, Wang Y, Zhou Q. Deep learning-based classification of nitrogen status in rice (Oryza sativa L.) using RGB imagery. Computers and Electronics in Agriculture. 2021; 186:106208. https://doi.org/10.1016/j.compag.2021.106208