Mapping twenty years of corn and soybean across the US Midwest using the Landsat archive

Abstract

Field-level monitoring of crop types in the United States via the Cropland Data Layer (CDL) has played an important role in improving production forecasts and enabling large-scale study of agricultural inputs and outcomes. Although CDL offers crop type maps across the conterminous US from 2008 onward, such maps are missing in many Midwestern states or are uneven in quality before 2008. To fill these data gaps, we used the now-public Landsat archive and cloud computing services to map corn and soybean at 30 m resolution across the US Midwest from 1999–2018. Our training data were CDL from 2008–2018, and we validated the predictions on CDL 1999–2007 where available, county-level crop acreage statistics, and state-level crop rotation statistics. The corn-soybean maps, which we call the Corn-Soy Data Layer (CSDL), are publicly hosted on Google Earth Engine and also available for download online.

Agricultural breadbaskets shift poleward given adaptive farmer behavior under climate change

“…To illustrate this, we show the case for maize in North America in Figure1. While maize is the second-most widely grown crop globally, with almost 200 Mha (Food and Agriculture Organization of the United Nations [FAO] (2020)) under cultivation, its production is highly concentrated, and the relatively small U.S.Corn Belt accounts for a full third of global production(Wang et al, 2020). The center of the U.S. Corn Belt is the state of Iowa, which produces 2.5× as much corn as all of Mexico (Food and Agriculture Organization of the United Nations [FAO] 2020; USDA National Agricultural Statistics Service, 2020).…”

Validation and refinement of cropland data layer using a spatial-temporal decision tree algorithm

“…Studies in recent years have demonstrated the possibility of refining existing crop mapping and predicting future or past planting information 9 , 20 . These studies utilized the historical archived remote sensing data and machine learning approaches, and results indicated the feasibility of improving the accuracy of CDL 9 , 20 – 23 .…”

“…Studies in recent years have demonstrated the possibility of refining existing crop mapping and predicting future or past planting information 9 , 20 . These studies utilized the historical archived remote sensing data and machine learning approaches, and results indicated the feasibility of improving the accuracy of CDL 9 , 20 – 23 . However, these methods usually only focus on a few crop types and are not scalable to border categories due to the shortage of training samples and labeled datasets 9 .…”

On the benefits of index insurance in US agriculture: a large-scale analysis using satellite data

“…The CDL crop map covers our nine states of interest in the Corn Belt, yet starts at different periods depending on the state, with starting dates ranging from 2000 to 2008. To have a consistent sample, we fill-in the missing years with the Corn-Soy Data Layer (CSDL) crop map of Wang et al (2020). The CSDL crop map uses random forests to predict corn and soybean from 2000 onwards for the nine states we consider here.…”