Leveraging Novel Ensemble Learning Techniques and Landsat Multispectral Data for Estimating Olive Yields in Tunisia

TL;DR

This paper presents a new ensemble machine learning pipeline utilizing Landsat multispectral data and digital elevation models to accurately estimate olive yields in Tunisia, demonstrating high predictive performance and scalability.

Contribution

It introduces a novel ensemble learning framework with Landsat data and elevation features for olive yield estimation, improving accuracy and efficiency over existing methods.

Findings

Landsat-8 achieved R2 = 0.8635 and RMSE = 1.17 tons/ha

Landsat-9 achieved R2 = 0.8378 and RMSE = 1.32 tons/ha

The method is scalable, cost-effective, and applicable to diverse regions.

Abstract

Olive production is an important tree crop in Mediterranean climates. However, olive yield varies significantly due to climate change. Accurately estimating yield using remote sensing and machine learning remains a complex challenge. In this study, we developed a streamlined pipeline for olive yield estimation in the Kairouan and Sousse governorates of Tunisia. We extracted features from multispectral reflectance bands, vegetation indices derived from Landsat-8 OLI and Landsat-9 OLI-2 satellite imagery, along with digital elevation model data. These spatial features were combined with ground-based field survey data to form a structured tabular dataset. We then developed an automated ensemble learning framework, implemented using AutoGluon to train and evaluate multiple machine learning models, select optimal combinations through stacking, and generate robust yield predictions using five-fold cross-validation. The results demonstrate strong predictive performance from both sensors, with Landsat-8 OLI achieving R2 = 0.8635 and RMSE = 1.17 tons per ha, and Landsat-9 OLI-2 achieving R2 = 0.8378 and RMSE = 1.32 tons per ha. This study highlights a scalable, cost-effective, and accurate method for olive yield estimation, with potential applicability across diverse agricultural regions globally.