Abstract
High resolution satellite imagery and modern machine learning methods hold the potential to fill existing data gaps in where crops are grown around the world at a sub-field level. However, high resolution crop type maps have remained challenging to create in developing regions due to a lack of ground truth labels for model development. In this work, we explore the use of crowdsourced data, Sentinel-2 and DigitalGlobe imagery, and convolutional neural networks (CNNs) for crop type mapping in India. Plantix, a free app that uses image recognition to help farmers diagnose crop diseases, logged 9 million geolocated photos from 2017–2019 in India, 2 million of which are in the states of Andhra Pradesh and Telangana in India. Crop type labels based on farmer-submitted images were added by domain experts and deep CNNs. The resulting dataset of crop type at coordinates is high in volume, but also high in noise due to location inaccuracies, submissions from out-of-field, and labeling errors. We employed a number of steps to clean the dataset, which included training a CNN on very high resolution DigitalGlobe imagery to filter for points that are within a crop field. With this cleaned dataset, we extracted Sentinel time series at each point and trained another CNN to predict the crop type at each pixel. When evaluated on the highest quality subset of crowdsourced data, the CNN distinguishes rice, cotton, and “other” crops with 74% accuracy in a 3-way classification and outperforms a random forest trained on harmonic regression features. Furthermore, model performance remains stable when low quality points are introduced into the training set. Our results illustrate the potential of non-traditional, high-volume/high-noise datasets for crop type mapping, some improvements that neural networks can achieve over random forests, and the robustness of such methods against moderate levels of training set noise. Lastly, we caution that obstacles like the lack of good Sentinel-2 cloud mask, imperfect mobile device location accuracy, and preservation of privacy while improving data access will need to be addressed before crowdsourcing can widely and reliably be used to map crops in smallholder systems.
Highlights
Smallholder farms—commonly defined as holdings smaller than 2 ha in size [1]—make up 84% of the world’s 570 million farms [2], provide a living for two-thirds of the world’s 3 billion rural population [3], and produce an estimated one-third of global food consumed [4,5]
We focus on developing crop type mapping methodology in two states: Andhra Pradesh and Telangana, where the Plantix app received the largest number of user submissions between 2017 and 2019 (Figure 1)
Pretrained convolutional neural networks fit to our in-field dataset (n = 2000) were able to classify whether the center boxes are in-field with high accuracy
Summary
Smallholder farms—commonly defined as holdings smaller than 2 ha in size [1]—make up 84% of the world’s 570 million farms [2], provide a living for two-thirds of the world’s 3 billion rural population [3], and produce an estimated one-third of global food consumed [4,5]. In the developing nations of Asia and Africa, smallholder agriculture is vital to achieving food security under growing populations [3] Relative to this global significance, there is a scarcity of data on smallholder crop production, starting at the fundamental questions of which crop types smallholders grow and where they grow them. Both pieces of information are needed to track smallholder yield progress, study management strategies, and design targeted agricultural policies [6,7]. Where official statistics on crop area and production do exist, they are aggregated to regional or national levels [9], or, in the case of the World Bank’s Living Standards Measurement Study, available for a random sample of a country’s villages [10]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.