Integration of artificial intelligence and remote sensing for crop yield prediction and crop growth parameter estimation in Mediterranean agroecosystems: Methodologies, emerging technologies, research gaps, and future directions

Abstract

Crop yield prediction (CYP) along with crop growth parameter estimation (CGPE) recently gained prominence as essential means for optimizing agricultural resource use and addressing global food security challenges, particularly in regions with vulnerable climates and diverse agricultural systems, such as the Mediterranean one. Artificial intelligence (AI) and remote sensing (RS) play an important role in achieving such objectives. To identify present methodologies and frameworks, emerging trends, research gaps and future directions in the integrated use of AI and RS in the Mediterranean area for CYP and CGPE. We systematically reviewed the published scientific literature on the topic (106 studies) by means of the PRISMA methodology. We found that integration of AI, particularly machine learning methods such as Random Forest, Support Vector Machine, and Artificial Neural Networks, along with satellite-based RS platforms such as Sentinel-2, Sentinel-1, MODIS, and Landsat-8, demonstrated strong potential to enhance monitoring and support adaptive agricultural decision-making. Deep learning models, such as Convolutional Neural Networks and Long Short Term Memories, are emerging tools for spatio-temporal modelling, although their use is limited, likely due to data and computational constraints. Wheat is the most frequently analyzed crop, alongside high-value perennial crops like olives and vineyards. Data acquisition relies predominantly on satellite imagery, though hybrid approaches incorporating unmanned aerial vehicle and ground-based data are promising in improving prediction accuracy. Despite these advancements, significant challenges persist, including uneven geographical research coverage, limited model transferability, and insufficient consideration of crop phenology. A critical lack of standardized validation datasets and the underrepresentation of North African and Middle Eastern countries further constrain progress. To fully harness AI-RS integration for sustainable agriculture and food security in the Mediterranean area, and similar agroecosystems, future efforts should aim at i) prioritizing cross-regional collaboration, ii) focusing on hybrid AI-RS methods, iii) developing phenology-aware models, and iv) widening access to data.

Plant phenotyping relevance

AI・リモートセンシングによる作物生育パラメータ推定を中心に、手法群・データ取得・検証課題を体系的にレビューしており、植物形質推定手法の方法論的レビューに該当する。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.