A scalable satellite-based crop yield mapper

Lobell, David B.; Thau, David; Seifert, Christopher; Engle, Eric; Little, Bertis B.

doi:10.1016/j.rse.2015.04.021

Cited by 435 publications

(234 citation statements)

References 27 publications

Supporting

Mentioning

226

Contrasting

Unclassified

Order By: Relevance

“…The accuracies achieved in this study are similar to those found in other studies that use automated approaches to map crop production and do not use any calibration data [34][35][36]. Though our previous work found that accuracies can likely improve when using classified Landsat satellite data for calibration [11], it is not feasible to use this calibration method across large spatial and temporal scales in an automated way because the Landsat satellite data needed for calibration are not available in every region and in every year due to issues with cloud cover ( Figure S1).…”

Section: Discussionsupporting

confidence: 86%

An Automated Approach to Map Winter Cropped Area of Smallholder Farms across Large Scales Using MODIS Imagery

et al. 2017

View full text Add to dashboard Cite

Fine-scale agricultural statistics are an important tool for understanding trends in food production and their associated drivers, yet these data are rarely collected in smallholder systems. These statistics are particularly important for smallholder systems given the large amount of fine-scale heterogeneity in production that occurs in these regions. To overcome the lack of ground data, satellite data are often used to map fine-scale agricultural statistics. However, doing so is challenging for smallholder systems because of (1) complex sub-pixel heterogeneity; (2) little to no available calibration data; and (3) high amounts of cloud cover as most smallholder systems occur in the tropics. We develop an automated method termed the MODIS Scaling Approach (MSA) to map smallholder cropped area across large spatial and temporal scales using MODIS Enhanced Vegetation Index (EVI) satellite data. We use this method to map winter cropped area, a key measure of cropping intensity, across the Indian subcontinent annually from 2000-2001 to 2015-2016. The MSA defines a pixel as cropped based on winter growing season phenology and scales the percent of cropped area within a single MODIS pixel based on observed EVI values at peak phenology. We validated the result with eleven high-resolution scenes (spatial scale of 5 × 5 m 2 or finer) that we classified into cropped versus non-cropped maps using training data collected by visual inspection of the high-resolution imagery. The MSA had moderate to high accuracies when validated using these eleven scenes across India (R 2 ranging between 0.19 and 0.89 with an overall R 2 of 0.71 across all sites). This method requires no calibration data, making it easy to implement across large spatial and temporal scales, with 100% spatial coverage due to the compositing of EVI to generate cloud-free data sets. The accuracies found in this study are similar to those of other studies that map crop production using automated methods and use no calibration data. To aid research on agricultural production at fine spatial scales in India, we make our annual winter crop maps from 2000-2001 to 2015-2016 at 1 × 1 km 2 produced in this study publically available through the NASA Socioeconomic Data and Applications Center (SEDAC) hosted by the Center for International Earth Science Information Network (CIESIN) at Columbia University. We also make our R script available since it is likely that this method can be used to map smallholder agriculture in other regions across the globe given that our method performed well in disparate agro-ecologies across India.

show abstract

Section: Discussionsupporting

confidence: 86%

An Automated Approach to Map Winter Cropped Area of Smallholder Farms across Large Scales Using MODIS Imagery

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Explana- 1 m. This indicates substantial benefit to using higher-resolution imagery for yield prediction in smallholder systems, but also suggests that lower-resolution imagery is not without value in the absence of alternatives. A second issue is whether one can avoid the need for ground calibration by instead using crop model simulations as training data (13). To test this, crop simulations were run for the study years using daily weather data from a local station and then used to estimate a regression model to predict yields from 1-m GCVI (Methods).…”

Section: Resultsmentioning

confidence: 99%

Satellite-based assessment of yield variation and its determinants in smallholder African systems

Burke

Lobell

2017

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

306

221

View full text Add to dashboard Cite

The emergence of satellite sensors that can routinely observe millions of individual smallholder farms raises possibilities for monitoring and understanding agricultural productivity in many regions of the world. Here we demonstrate the potential to track smallholder maize yield variation in western Kenya, using a combination of 1-m Terra Bella imagery and intensive field sampling on thousands of fields over 2 y. We find that agreement between satellite-based and traditional field survey-based yield estimates depends significantly on the quality of the field-based measures, with agreement highest (R 2 up to 0.4) when using precise field measures of plot area and when using larger fields for which rounding errors are smaller. We further show that satellite-based measures are able to detect positive yield responses to fertilizer and hybrid seed inputs and that the inferred responses are statistically indistinguishable from estimates based on survey-based yields. These results suggest that high-resolution satellite imagery can be used to make predictions of smallholder agricultural productivity that are roughly as accurate as the survey-based measures traditionally used in research and policy applications, and they indicate a substantial near-term potential to quickly generate useful datasets on productivity in smallholder systems, even with minimal or no field training data. Such datasets could rapidly accelerate learning about which interventions in smallholder systems have the most positive impact, thus enabling more rapid transformation of rural livelihoods.agriculture | yield gaps | remote sensing | maize | Africa I mproving the productivity of smallholder farmers is thought to be a key component of the effort to reduce global poverty and increase food security (1). Despite the importance of agriculture in these dual goals, however, the productivity of most smallholders around the world remains poorly measured. Agricultural statistics at the national level in developing countries are often unreliable and tend to be poorest in countries where productivity improvements are most needed (2), and systematic data at the subnational or field scale are unavailable in most of these countries. This absence of data on agriculture is a serious constraint to both research and policy, making it difficult to measure productivity gaps, understand why these gaps exist, and evaluate programs aimed at improving overall productivity.Various strategies have been proposed to plug these data gaps. One promising approach has been the design and implementation of a new wave of nationally representative household panel surveys that contain detailed agricultural modules (3). These ongoing surveys, orchestrated by the World Bank and currently under implementation across multiple African countries, promise to increase understanding of African agriculture. Another approach has been the implementation of smaller-scale and more targeted data collection efforts, for instance to measure the productivity impact of a farm-level intervention in a...

show abstract

“…Here, we used the mean temperature ( ) from May through July; precipitation and vapor pressure deficit were not significant at both the B-K sub-region and the 1AF region based on our preliminary analysis, thus, were excluded from the model. The second approach, referred to as the "uncalibrated" approach, used a well-validated crop model to generate pseudo-observations of yields and VIs to derive the regression coefficients of β in Equations (1) [6,7]. In this way, ground-measured yield was no longer …”

Section: Satellite Based Yield Estimationmentioning

confidence: 99%

Mapping Smallholder Yield Heterogeneity at Multiple Scales in Eastern Africa

et al. 2017

View full text Add to dashboard Cite

Accurate measurements of crop production in smallholder farming systems are critical to the understanding of yield constraints and, thus, setting the appropriate agronomic investments and policies for improving food security and reducing poverty. Nevertheless, mapping the yields of smallholder farms is challenging because of factors such as small field sizes and heterogeneous landscapes. Recent advances in fine-resolution satellite sensors offer promise for monitoring and characterizing the production of smallholder farms. In this study, we investigated the utility of different sensors, including the commercial Skysat and RapidEye satellites and the publicly accessible Sentinel-2, for tracking smallholder maize yield variation throughout a~40,000 km 2 western Kenya region. We tested the potential of two types of multiple regression models for predicting yield: (i) a "calibrated model", which required ground-measured yield and weather data for calibration, and (ii) an "uncalibrated model", which used a process-based crop model to generate daily vegetation index and end-of-season biomass and/or yield as pseudo training samples. Model performance was evaluated at the field, division, and district scales using a combination of farmer surveys and crop cuts across thousands of smallholder plots in western Kenya. Results show that the "calibrated" approach captured a significant fraction (R 2 between 0.3 and 0.6) of yield variations at aggregated administrative units (e.g., districts and divisions), while the "uncalibrated" approach performed only slightly worse. For both approaches, we found that predictions using the MERIS Terrestrial Chlorophyll Index (MTCI), which included the red edge band available in RapidEye and Sentinel-2, were superior to those made using other commonly used vegetation indices. We also found that multiple refinements to the crop simulation procedures led to improvements in the "uncalibrated" approach. We identified the prevalence of small field sizes, intercropping management, and cloudy satellite images as major challenges to improve the model performance. Overall, this study suggested that high-resolution satellite imagery can be used to map yields of smallholder farming systems, and the methodology presented in this study could serve as a good foundation for other smallholder farming systems in the world.

show abstract

A scalable satellite-based crop yield mapper

Cited by 435 publications

References 27 publications

An Automated Approach to Map Winter Cropped Area of Smallholder Farms across Large Scales Using MODIS Imagery

An Automated Approach to Map Winter Cropped Area of Smallholder Farms across Large Scales Using MODIS Imagery

Satellite-based assessment of yield variation and its determinants in smallholder African systems

Mapping Smallholder Yield Heterogeneity at Multiple Scales in Eastern Africa

Contact Info

Product

Resources

About