A Multi-Stage AI Framework for Solar Energy Prediction and Smart Irrigation Scheduling with Economic and Land Optimization

DOI

10.2991/978-94-6239-791-0_24How to use a DOI?

Keywords

Solar Energy Prediction; Smart Irrigation; LSTM; Precision Agriculture; Renewable Energy

Abstract

Effective management of water and energy resources has become an important issue for contemporary agriculture, especially with regard to the emergence of renewable energy sources such as solar energy. Nevertheless, the intermittency of solar energy can affect the process of providing energy supply in order to sustain agricultural irrigation systems. This paper presents an approach for solar energy prediction and scheduling of irrigations by using an AI system that consists of multiple stages. Specifically, the system includes an LSTM model and a Random Forest model for forecasting solar energy availability in real time and predicting daily energy production, respectively. Solar energy forecasts are transformed into actual energy production taking into consideration the photovoltaic properties of panels. Moreover, the proposed framework employs a decision-making system for scheduling irrigation in accordance with the availability of energy, water needs, and time of the day without scheduling irrigation during times of high temperatures. In addition, the framework takes into consideration an advisory system for energy management and agrivoltaics land optimization analysis. Experimental findings reveal high levels of prediction accuracy where the R2 values for both the Random Forest and LSTM models are 0.9896 and 0.819 respectively. The introduced model is efficient in enhancing energy consumption from renewable sources, lowering cost, and sustainable precision farming practices. Besides, the model is aligned with SDGs 2, 7, and 12 since it ensures efficient use of resources in agriculture.

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  - Karthik Kurup
AU  - Maya Kurulekar
AU  - Mahesh Kurulekar
PY  - 2026
DA  - 2026/10/09
TI  - A Multi-Stage AI Framework for Solar Energy Prediction and Smart Irrigation Scheduling with Economic and Land Optimization
BT  - Proceedings of the International Conference on Artificial Intelligence and Machine Learning for Agro-Ecosystems (ICAIML-AE 2026)
PB  - Atlantis Press
SP  - 310
EP  - 320
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-791-0_24
DO  - 10.2991/978-94-6239-791-0_24
ID  - Kurup2026
ER  -