Legume Research

Legume Research cover
Volume 49 · 2026/06/18

Integrated Nutrient Management for Sustainable Production and Soil Health in Intercropped Lentil-sorghum Systems: A Field-validated Machine Learning Approach

P. Nithya
M. Meenakshi
M. Mageshwari
S. Sekar
277 Views

Submitted

2026/05/07

First Online

2026/06/18

doi

10.18805/LR-5677

Cite article - P. Nithya, M. Meenakshi, M. Mageshwari, S. Sekar. (2026). Integrated Nutrient Management for Sustainable Production and Soil Health in Intercropped Lentil-sorghum Systems: A Field-validated Machine Learning Approach. Legume Research. 49: 01–09. doi: 10.18805/LR-5677

Abstract

Background: In South Asia, where semi-aridity predominates, cereal-lentil mixtures have been widely employed in traditional agricultural practices for many years, with the lentil-sorghum system being highly relevant in areas of shallow soils, unpredictable monsoons and lack of inputs making crop production alone difficult. Input application regimes developed for mono-cropping, when blindly used in mixed cropping systems, result in over-nitrogenating of the leguminous row crops, inhibit nodule formation and continually decrease soil biological quality, but there is no quantitative method based on practical evidence that could guide farmers with regards to input management in this special case.

Methods: With this problem in mind, we examined seven different nutrient management schemes varying from complete to partial use of chemical fertilizers combined with organic amendments in two subsequent seasons of the kharif cycle, along with training a random forest-long short-term Memory model using 2,184 seasonal plot records to forecast lentil equivalent yields based on soil, crop and weather factors.

Result: The proposed model held R² = 0.93 and RMSE = 112 kg ha -1 on unseen data. In the field, pairing 75% of the recommended fertiliser dose with farmyard manure at 5 t ha -1 and rhizobium-PSB seed inoculation returned the strongest lentil equivalent yield (3,842 kg ha -1 ), land equivalent ratio (1.48) and net income (Rs 68,450 ha -1 ). Dehydrogenase activity and microbial biomass carbon climbed 60.7% and 72.8% above sole chemical plots. Shapley attribution then pointed to farmyard manure rate, soil organic carbon at sowing and accumulated heat units as the variables most responsible for yield differences across treatments.

References

  1. Akchaya, K., Parasuraman, P., Pandian, K., Vijayakumar, S., Thirukumaran, K., Mustaffa, M.R.A.F., Rajpoot, S.K. and Choudhary, A.K. (2025). Boosting resource use efficiency, soil fertility, food security and sustainability through legume intercropping: A review. Frontiers in Sustainable Food Systems . 9: 1527256. Bargaz, A., Lyamlouli, K., Chtouki, M., Zeroual, Y. and Dhiba, D. (2018). Soil microbial resources for improving fertilizers efficiency in an integrated plant nutrient management system. Frontiers in Microbiology. 9: 1606. Bedoussac, L., Journet, E.P., Constantin, J. and Justes, E. (2021). Cereal-legume intercropping performance under reduced nitrogen inputs: A multi-site analysis with APSIM. European Journal of Agronomy . 130: 126366. Birhanu, M.W. (2024). Arbuscular mycorrhizal (AM) fungi symbiosis in sustainable production of sorghum ( Sorghum bicolor L. Moench) under drought stress: An emerging biofertilizer in dryland areas. Journal of Environmental and Agricultural Studies . 6(4): 1-15. Cho, O.H. (2024). An evaluation of various machine learning approaches for detecting leaf diseases in agriculture. Legume Research. 47(4): 619-627. doi: 10.18805/LRF-787 . Corrales, D.C., Schoving, C., Raynal, H., Debaeke, P., Journet, E.P. and Constantin, J. (20220. A surrogate model based on feature selection techniques and regression learners to improve soybean yield prediction in southern France. Computers and Electronics in Agriculture . 192: 106578. Drees, L., Demie, D.T., Paul, M.R., Leonhardt, J., Seidel, S.J. and Döring, T.F. (2024). Data-driven crop growth simulation on time-varying generated images using multi-conditional generative adversarial networks. Plant Methods . 20: 93. Droutsas, I., Challinor, A.J., Deva, C.R. and Wang, E. (2022). Integration of machine learning into process-based modelling to improve simulation of complex crop responses. In silico Plants. 4: diac017. Ennaji, O., Vergutz, L. and El Allali, A. (2023). Machine learning in nutrient management: A review. Artificial Intelligence in Agriculture. 9: 1-11. Gaba, S., Lescourret, F., Boudsocq, S., Enjalbert, J. and Hinsinger, P. (2015). Multiple cropping systems as drivers for providing multiple ecosystem services: From concepts to design. Agronomy for Sustainable Development . 35(2): 607-623. Kukkar, A., Mohana, R. and Sharma, A. (2024). AgroAdvisor: Crop yield prediction, crop and fertilizer recommendation system using random forest with gradient boosting and DeepFM for precise agriculture. Research Square . https://doi.org/10.21203/rs.3.rs-4099720/v1. Kuradusenge, M., Hitimana, E., Hanyurwimfura, D., Rukundo, P., Mtonga, K. and Mukasine, A. (2023). Crop yield prediction using machine learning models: Case of Irish potato and maize. Agriculture . 13: 225. Prodhan, F.A., Zhang, J., Sharma, T.P.P., Nanzad, L. and Zhang, D. (2022). Projection of future drought and its impact on simulated crop yield over South Asia using ensemble machine learning approach. Science of the Total Environment . 807: 151029. Sharma, J.P., Gupta, R.K., Kumar, A. and Singh, A.K. (2021). Organic amendments and microbial inoculants influence dehydrogenase activity and microbial biomass carbon in semi-arid soils under lentil cultivation. Communications in Soil Science and Plant Analysis. 52(8): 879-892. Sivakumar, V.G., Baskar, V.V., Vadivel, M., Vimal, S.P. and Murugan, S. (2023). IoT and GIS Integration for Real-Time Monitoring of Soil Health and Nutrient Status. In: Proceedings of ICSSAS 2023, IEEE, pp 1265-1270. Sodavadiya, H.B., Patel, V.J. and Sadhu, A.C. (2023). Effect of integrated nutrient management on the growth and yield of chickpea ( Cicer arietinum L.) under chickpea-forage sorghum ( Sorghum bicolor L.) cropping sequence. Legume Research. 46(12): 1617-1622. doi: 10.18805/LR-4465 . Sujathamma, P. and Nedunchezhiyan, M. (2024). Evaluation of sorghum based intercropping systems for rainfed vertisols. Indian Journal of Agricultural Research. 58(2): 290-294. doi: 10.18805/IJARe.A-5934 .
EDITORIAL BOARD

Guided by Experienced Academic Leadership

Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.

View Full Board
Kadambot Siddique
Chief Editor

Kadambot Siddique

DirectorThe UWA Institute of Agriculture, The University of Western Australia, AUSTRALIA

Pei Xu
Associate chief editor

Pei Xu

DeanChina Jiliang University, CHINA

Satpal Singh Bisht
Editor

Satpal Singh Bisht

Vice ChancellorS.S.J.University Almora, Uttarakhand, INDIA

H.K. Dikshit
Editor

H.K. Dikshit

Principal Scientist Indian Agricultural Research Institute, New Delhi, INDIA