The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series

2026-03-25

AI Summary

This study addresses the challenge of effectively distinguishing organic from conventional agricultural systems using remote sensing data, while investigating the influence of crop type and spatial context on classification performance. Leveraging Sentinel-2 multispectral time-series imagery, the authors propose an enhanced spatiotemporal Vision Transformer (TSViT) model that jointly predicts farming system and crop type through multitask learning. The impact of spatial context and the multitask mechanism is systematically evaluated across varying spatial window scales. The work reveals, for the first time, that expanding spatial context substantially improves performance on both tasks—achieving F1 scores ≥0.8 for crops such as winter rye and winter wheat—whereas the benefits of multitask learning are limited. These findings indicate that incorporating broader spatial information holds greater potential than multitask architectures for enhancing the remote sensing–based identification of farming systems.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Organic farming is a key element in achieving more sustainable agriculture. For a better understanding of the development and impact of organic farming, comprehensive, spatially explicit information is needed. This study presents an approach for the discrimination of organic and conventional farming systems using intra-annual Sentinel-2 time series. In addition, it examines two factors influencing this discrimination: the joint learning of crop type information in a concurrent task and the role of spatial context. A Vision Transformer model based on the Temporo-Spatial Vision Transformer (TSViT) architecture was used to construct a classification model for the two farming systems. The model was extended for simultaneous learning of the crop type, creating a multitask learning setting. By varying the patch size presented to the model, we tested the influence of spatial context on the classification accuracy of both tasks. We show that discrimination between organic and conventional farming systems using multispectral remote sensing data is feasible. However, classification performance varies substantially across crop types. For several crops, such as winter rye, winter wheat, and winter oat, F1 scores of 0.8 or higher can be achieved. In contrast, other agricultural land use classes, such as permanent grassland, orchards, grapevines, and hops, cannot be reliably distinguished, with F1 scores for the organic management class of 0.4 or lower. Joint learning of farming system and crop type provides only limited additional benefits over single-task learning. In contrast, incorporating wider spatial context improves the performance of both farming system and crop type classification. Overall, we demonstrate that a classification of agricultural farming systems is possible in a diverse agricultural region using multispectral remote sensing data.

Problem

• organic farming
• conventional farming
• Sentinel-2 time series
• spatial context
• multitask learning

Innovation

• Vision Transformer
• multitask learning
• spatial context
• Sentinel-2 time series
• organic farming classification