High-Resolution Satellite Imagery for Modeling the Impact of Aridification on Crop Production

TL;DR

This paper introduces SICKLE, a comprehensive satellite imagery dataset for paddy cultivation in Tamil Nadu, and demonstrates its use in improving crop parameter predictions through machine learning models that incorporate domain-specific growing season data.

Contribution

The paper presents the first curated, multi-spectral satellite dataset with detailed cropping annotations for paddy, and develops a yield prediction method leveraging growing season information.

Findings

Benchmarking on crop type, phenology, and yield prediction tasks.

Performance improvements using domain knowledge of growing seasons.

Demonstration of ML models effectively utilizing multi-spectral satellite data.

Abstract

The availability of well-curated datasets has driven the success of Machine Learning (ML) models. Despite the increased access to earth observation data for agriculture, there is a scarcity of curated, labelled datasets, which limits the potential of its use in training ML models for remote sensing (RS) in agriculture. To this end, we introduce a first-of-its-kind dataset, SICKLE, having time-series images at different spatial resolutions from 3 different satellites, annotated with multiple key cropping parameters for paddy cultivation for the Cauvery Delta region in Tamil Nadu, India. The dataset comprises of 2,398 season-wise samples from 388 unique plots distributed across 4 districts of the Delta. The dataset covers multi-spectral, thermal and microwave data between the time period January 2018-March 2021. The paddy samples are annotated with 4 key cropping parameters, i.e. sowing date, transplanting date, harvesting date and crop yield. This is one of the first studies to consider the growing season (using sowing and harvesting dates) as part of a dataset. We also propose a yield prediction strategy that uses time-series data generated based on the observed growing season and the standard seasonal information obtained from Tamil Nadu Agricultural University for the region. The consequent performance improvement highlights the impact of ML techniques that leverage domain knowledge that are consistent with standard practices followed by farmers in a specific region. We benchmark the dataset on 3 separate tasks, namely crop type, phenology date (sowing, transplanting, harvesting) and yield prediction, and develop an end-to-end framework for predicting key crop parameters in a real-world setting.