HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing

TL;DR

HarvestNet introduces a new dataset and method for detecting smallholder farms by identifying harvest piles in satellite images, improving cropland mapping accuracy in developing regions.

Contribution

The paper presents HarvestNet, a novel dataset and benchmark for detecting smallholder farming activity using harvest pile detection in satellite imagery.

Findings

Achieved around 80% classification performance on labeled data.

Detected an additional 56,621 hectares of cropland compared to existing maps.

Models reached 90% and 98% accuracy on ground truth data for Tigray and Amhara.

Abstract

Small farms contribute to a large share of the productive land in developing countries. In regions such as sub-Saharan Africa, where 80\% of farms are small (under 2 ha in size), the task of mapping smallholder cropland is an important part of tracking sustainability measures such as crop productivity. However, the visually diverse and nuanced appearance of small farms has limited the effectiveness of traditional approaches to cropland mapping. Here we introduce a new approach based on the detection of harvest piles characteristic of many smallholder systems throughout the world. We present HarvestNet, a dataset for mapping the presence of farms in the Ethiopian regions of Tigray and Amhara during 2020-2023, collected using expert knowledge and satellite images, totaling 7k hand-labeled images and 2k ground-collected labels. We also benchmark a set of baselines, including SOTA models in remote sensing, with our best models having around 80\% classification performance on hand labelled data and 90\% and 98\% accuracy on ground truth data for Tigray and Amhara, respectively. We also perform a visual comparison with a widely used pre-existing coverage map and show that our model detects an extra 56,621 hectares of cropland in Tigray. We conclude that remote sensing of harvest piles can contribute to more timely and accurate cropland assessments in food insecure regions. The dataset can be accessed through https://figshare.com/s/45a7b45556b90a9a11d2, while the code for the dataset and benchmarks is publicly available at https://github.com/jonxuxu/harvest-piles