Fallow-land Algorithm based on Neighborhood and TemporalAnomalies (FANTA) to map planted versus fallowed croplands usingMODIS data to assist in drought studies leading to water and foodsecurity assessments

Cynthia Wallace; Prasad S. Thenkabail; Jesus R. Rodriguez; Melinda K. Brown

doi:10.1080/15481603.2017.1290913

Home/Archive/USGS

USGS · 70186183

Fallow-land Algorithm based on Neighborhood and TemporalAnomalies (FANTA) to map planted versus fallowed croplands usingMODIS data to assist in drought studies leading to water and foodsecurity assessments

Cynthia Wallace·Prasad S. Thenkabail·Jesus R. Rodriguez·Melinda K. Brown

View original source ↗Export metadata ↓

Abstract

An important metric to monitor for optimizing water use in agricultural areas is the amount of cropland left fallowed, or unplanted. Fallowed croplands are difficult to model because they have many expressions; for example, they can be managed and remain free of vegetation or be abandoned and become weedy if the climate for that season permits. We used 250 m, 8-day composite Moderate Resolution Imaging Spectroradiometer normalized difference vegetation index data to develop an algorithm that can routinely map cropland status (planted or fallowed) with over 75% user’s and producer’s accuracies. The Fallow-land Algorithm based on Neighborhood and Temporal Anomalies (FANTA) compares the current greenness of a cultivated pixel to its historical greenness and to the greenness of all cultivated pixels within a defined spatial neighborhood, and is therefore transportable across space and through time. This article introduces FANTA and applies it to California from 2001 to 2015 as a case study for use in data-poor places and for use in historical modeling. Timely and accurate knowledge of the extent of fallowing can provide decision makers with insights and knowledge to mitigate the impacts of drought and provide a scientific basis for effective management response. This study is part of the WaterSMART (Sustain and Manage America’s Resources for Tomorrow) project, an interdisciplinary and collaborative research effort focused on improving water conservation and optimizing water use.

Explore related subjects

GIScience and Remote Sensing Article

Source-reported bounding extent: 34.813803317113155° to 40.88029480552824° latitude; -123.01391601562499° to -118.16894531249999° longitude. This indicates report coverage, not an exact sampling location. View area on OpenStreetMap.

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Cynthia Wallace, Prasad S. Thenkabail, Jesus R. Rodriguez, Melinda K. Brown. 2017-03-15. Fallow-land Algorithm based on Neighborhood and TemporalAnomalies (FANTA) to map planted versus fallowed croplands usingMODIS data to assist in drought studies leading to water and foodsecurity assessments. https://doi.org/10.1080/15481603.2017.1290913

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2019

Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud

The South Asia (India, Pakistan, Bangladesh, Nepal, Sri Lanka and Bhutan) has a staggering 900 million people (~43% of the population) who face food insecurity or severe food insecurity as per United Nations, Food and Agriculture Organization’s (FAO) the Food Insecurity Experience Scale (FIES). The existing coarse-resolution (>250-m) cropland maps lack precision in geo-location of individual farms and have low map accuracies. This also results in uncertainties in cropland areas calculated from such products. Thereby, the overarching goal of this study was to develop high spatial resolution (30-m or better) baseline cropland extent product of South Asia for the year 2015 using Landsat satellite time-series big-data and machine learning algorithms (MLAs) on the Google Earth Engine (GEE) cloud computing platform. To eliminate the impact of clouds, ten time-composited Landsat bands (blue, green, red, NIR, SWIR1, SWIR2, Thermal, EVI, NDVI, NDWI) were derived for each of the 3 time-periods over 12 months (monsoon: Julian days 151-300; winter: Julian days 301-365 plus 1-60; and summer: Julian days 61-150), taking the every 8-day data from Landsat-8 and 7 for the years 2013-2015, for a total of 30-bands plus global digital elevation model (GDEM) derived slope band. This 31-band mega-file big data-cube was composed for each of the 5 agro-ecological zones (AEZ’s) of South Asia and formed a baseline data for image classification and analysis. Knowledge-base for the Random Forest (RF) MLAs were developed using spatially well spread-out reference training data (N=2179) in 5 AEZs. Classification was performed on GEE for each of the 5 AEZs using well-established knowledge-based and RF MLAs on the cloud. Map accuracies were measured using independent validation data (N=1185). The survey showed that the South Asia cropland product had a producer’s accuracy of 89.9% (errors of omissions of 10.1%), user’s accuracy of 95.3% (errors of commission of 4.7%) and an overall accuracy of 88.7%. The National and sub-national (districts) areas computed from this cropland extent product explained 80-96% variability when compared with the National statistics of the South Asian Countries. The full resolution imagery can be viewed at full-resolution, by zooming-in to any location in South Asia or the world, at www.croplands.org and the cropland products of South Asia downloaded from The Land Processes Distributed Active Archive Center (LP DAAC) of National Aeronautics and Space Administration (NASA) and the United States Geological Survey (USGS): https://lpdaac.usgs.gov/products/gfsad30saafgircev001/

GIScience and Remote Sensing↗

USGS2019

Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.

GIScience and Remote Sensing↗

USGS2018

Mapping cropland fallow areas in myanmar to scale up sustainable intensification of pulse crops in the farming system

Cropland fallows are the next best-bet for intensification and extensification, leading to increased food production and adding to the nutritional basket. The agronomical suitability of these lands can decide the extent of usage of these lands. Myanmar’s agricultural land (over 13.8 Mha) has the potential to expand by another 50% into additional fallow areas. These areas may be used to grow short-duration pulses, which are economically important and nutritionally rich, and constitute the diets of millions of people as well as provide an important source of livestock feed throughout Asia. Intensifying rice fallows will not only improve the productivity of the land but also increase the income of the smallholder farmers. The enhanced cultivation of pulses will help improve nutritional security in Myanmar and also help conserve natural resources and reduce environmental degradation. The objectives of this study was to use remote sensing methods to identify croplands in Myanmar and cropland fallow areas in two important agro-ecological regions, delta and coastal region and the dry zone. The study used moderate-resolution imaging spectroradiometer (MODIS) 250-m, 16-day normalized difference vegetation index (NDVI) maximum value composite (MVC), and land surface water index (LSWI) for one 1 year (1 June 2012–31 May 2013) along with seasonal field-plot level information and spectral matching techniques to derive croplands versus cropland fallows for each of the three seasons: the monsoon period between June and October; winter period between November and February; and summer period between March and May. The study showed that Myanmar had total net cropland area (TNCA) of 13.8 Mha. Cropland fallows during the monsoon season account for a meagre 2.4% of TNCA. However, in the winter season, 56.5% of TNCA (or 7.8 Mha) were classified as cropland fallows and during the summer season, 82.7% of TNCA (11.4 Mha) were cropland fallows. The producer’s accuracy of the cropland fallow class varied between 92 and 98% (errors of omission of 2 to 8%) and user’s accuracy varied between 82 and 92% (errors of commission of 8 to 18%) for winter and summer, respectively. Overall, the study estimated 19.2 Mha cropland fallows from the two major seasons (winter and summer). Out of this, 10.08 Mha has sufficient moisture (either from rainfall or stored soil water content) to grow short-season pulse crops. This potential with an estimated income of US\$ 300 per hectare, if exploited sustainably, is estimated to bring an additional net income of about US\$ 1.5 billion to Myanmar per year if at least half (5.04 Mha) of the total cropland fallows (10.08 Mha) is covered with short season pulses.

GIScience and Remote Sensing↗