Satellite imagery-driven models support chickpea farmers in the field

A new study introduces a machine learning tool that combines satellite imagery and weather data to monitor chickpea crop health. The system accurately estimates Leaf Area Index (LAI) and Leaf Water Potential (LWP) across commercial fields, helping farmers make smarter irrigation decisions and improve yields. This research marks the first large-scale application of such technology in chickpea farming.

A new study published in the European Journal of Agronomy offers chickpea farmers a powerful tool to make smarter irrigation decisions and improve crop performance, thanks to satellite data and machine learning.

Led by PhD candidate Omer Perach under the supervision of Dr. Ittai Herrmann at the Robert H. Smith Institute of Plant Sciences and Genetics in Agriculture, Faculty of Agriculture Food and Environment, at The Hebrew University of Jerusalem, the research integrates high-resolution Sentinel-2 satellite imagery with weather data to estimate key plant health indicators: Leaf Area Index (LAI) and Leaf Water Potential (LWP). These indicators play a critical role in understanding canopy development and water stress in chickpea, a vital crop for semi-arid regions worldwide.

By combining data science with agronomy, the researchers developed machine learning models that can predict field-wide physiological conditions across commercial chickpea fields. Crucially, they tested the models using a "leave-field-out" strategy, mimicking real-world conditions where new fields have not previously been used to train the models, making the tool relevant and reliable for practical use.

“Our goal was to create something that doesn’t just work in the lab but helps farmers in the field,” said lead author Omer Perach. “With this system, we can offer growers spatial maps of plant development and water status across their entire field. This kind of information allows for more precise and timely irrigation.”

The models achieved high accuracy for estimating Leaf Area Index and were able to distinguish between different levels of water stress, even under real-world variability across 17 commercial fields. By overlaying physiological maps with irrigation schedules, the researchers showed how farmers could preemptively respond to crop needs and improve yield outcomes.

“The response of chickpea plants to irrigation regimes can be observed from space,” said Dr. Ittai Herrmann. “What we’ve developed is a scalable way to detect within-field variability using free satellite data and standard weather station inputs. This helps transform intuition-based farming into data-driven management.”

The study lays the groundwork for integrating these models into platforms like Google Earth Engine, where they can be accessed by farmers globally, even in regions with limited technical infrastructure.

The research was supported by the Hebrew University Intramural Research Fund, the Association of Field Crop Farmers in Israel, and the Chief Scientist of the Israeli Ministry of Agriculture and Food Security.