AI-Driven Predictive Analytics for Crop Rotation and Soil Health Management

DOI

10.2991/978-94-6239-624-1_18How to use a DOI?

Keywords

Crop rotation; soil degradation; ICRISAT; ConvLSTM; GRU

Abstract

Agricultural sustainability faces mounting challenges from climate change, soil degradation, and the growing demand for food production. Crop rotation has long been recognized as an effective practice for enhancing soil fertility, mitigating pest infestations, and boosting yields. However, traditional rotation planning relies heavily on farmer experience and static guidelines, which often fail to account for dynamic variables such as climate variability, market conditions, and evolving soil health profiles. Recent advances in Artificial Intelligence (AI) and predictive analytics offer a transformative approach to optimizing these decisions through data-driven modeling. This study proposes a hybrid Convolutional Long Short-Term Memory (ConvLSTM) model that integrates Conv1D layers for short-term temporal feature extraction with LSTM layers for long-term dependency modeling. The methodology utilizes multi-year agricultural time-series data from the International Crops Research Institute for the Semi-Arid Tropics (ICRISAT), encompassing production, yield, and cultivated area across key crop types. Experimental results demonstrate that the proposed ConvLSTM achieves superior classification performance, attaining an overall accuracy of 94.8%, outperforming traditional LSTM, GRU, and machine learning baselines. Class-wise evaluations reveal particularly high precision and recall in major crops such as rice, wheat, and pearl millet, alongside stable convergence patterns with minimal overfitting. These findings highlight the potential of ConvLSTM-based predictive analytics to revolutionize crop rotation planning by providing scalable, accurate, and adaptive recommendations. Such systems could serve as essential tools for promoting sustainable agriculture, enhancing productivity, and improving resilience to climate-induced disruptions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Anseena Anees Sabeena
AU  - Md Azharul Islam
AU  - Rukshanda Rahman
AU  - Sadia Sharmin
AU  - Anupom Debnath
AU  - Durga Shahi
AU  - Arif Ahmed Sizan
AU  - Arifa Ahmed
PY  - 2026
DA  - 2026/04/06
TI  - AI-Driven Predictive Analytics for Crop Rotation and Soil Health Management
BT  - Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
PB  - Atlantis Press
SP  - 254
EP  - 265
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-624-1_18
DO  - 10.2991/978-94-6239-624-1_18
ID  - Sabeena2026
ER  -