Anticipatory Understanding of Resilient Agriculture to Climate

TL;DR

This paper describes a framework to better identify food security hotspots using a combination of remote sensing, deep learning, crop yield modeling, and causal modeling of the food distribution system in India.

Abstract

With billions of people facing moderate or severe food insecurity, the resilience of the global food supply will be of increasing concern due to the effects of climate change and geopolitical events. In this paper we describe a framework to better identify food security hotspots using a combination of remote sensing, deep learning, crop yield modeling, and causal modeling of the food distribution system. While we feel that the methods are adaptable to other regions of the world, we focus our analysis on the wheat breadbasket of northern India, which supplies a large percentage of the world's population. We present a quantitative analysis of deep learning domain adaptation methods for wheat farm identification based on curated remote sensing data from France. We model climate change impacts on crop yields using the existing crop yield modeling tool WOFOST and we identify key drivers of crop simulation error using a longitudinal penalized functional regression. A description of a system dynamics model of the food distribution system in India is also presented, along with results of food insecurity identification based on seeding this model with the predicted crop yields.

Figures (36)

• Figure 1: Crop type classification datasets are spread across many domains and formats, requiring specialized preprocessing to homogenize data for consistent usage.
• Figure 2: The three focus states in Northern India encompass several different geographies.
• Figure 3: France's RPG dataset provides parcel-level crop type annotations for the full country.
• Figure 4: Wheat parcels rotate across years, deeming it necessary to use specific inidividual year's imagery and labels.
• Figure 5: The tuned S2Cloudless model can capture most or all cloud instances and cloud types in its per-pixel mask, where the default Sentinel-2 vector cloud mask fails. The green ovals in S2Cloudless highlight the clouds that are successfully masked that are incorrectly missed in the red ovals of ESA.