Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains

Wardlow, Brian D.; Egbert, Stephen L.

doi:10.1016/j.rse.2007.07.019

Cited by 629 publications

(378 citation statements)

References 46 publications

Supporting

Mentioning

350

Contrasting

Unclassified

Order By: Relevance

“…Therefore, methodologies for the reduction, or selection, of the data used in the former can be transferred to the optimisation of data acquired over a period of time. Hyper-temporal data are generated from a platform which offers a high temporal resolution and a sufficiently long time-series such as AVHRR (Hill et al 1999;Hermance et al, 2007), MERIS (Zurita-Milla et al, 2009;Carrão et al, 2010;O'Connor et al, 2012) or MODIS (Lunetta et al, 2006;Carrão et al, 2008;Wardlow and Egbert, 2008;Pringle et al, 2012). Typically, Normalized Difference Vegetation Index (NDVI) or other sensor-specific vegetation indices (VI) serve as the base for land-cover and crop type classification or phenological analysis from regional to global scales.…”

Section: Introductionmentioning

confidence: 99%

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Nitze

Barrett

Cawkwell

2015

International Journal of Applied Earth Observation and Geoinfor

116

View full text Add to dashboard Cite

Abstract:The analysis and classification of land cover is one of the principal applications in terrestrial remote sensing. Due to the seasonal variability of different vegetation types, the ability to discriminate different land cover types changes over time. Multi-temporal classification can help to improve the classification accuracies, but different constraints, such as financial restrictions or atmospheric conditions, may limit their application. The optimisation of image acquisition timing and frequencies can help to increase the effectiveness of the classification process. For this purpose, the Feature Importance measure of the state-of-the art machine learning method Random Forest was used to determine the optimal image acquisition periods for a general (Grassland, Forest, Water, Settlement, Peatland) and grassland specific (Improved Grassland, Semi-Improved Grassland) land cover classification in central Ireland on a 9-year time-series of MODIS Terra 16 day composite data (MOD13Q1). Feature Importances for each acquisition period of the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) were calculated for both classification scenarios. In the general land cover classification, the months December and January showed the highest, and July and August the lowest separability for both VIs over the entire nine-year period. This temporal separability was reflected in the classification accuracies, where the optimal choice of image dates outperformed the worst image date by 13% using NDVI and 5% using EVI on a mono-temporal analysis. With the addition of the next best image periods to the data input the classification accuracies converged quickly to their limit at around 8 to 10 images. The binary classification schemes, using two classes only, showed a stronger seasonal dependency with a higher intra-annual, but lower inter-annual variation. Nonetheless anomalous weather conditions, such as the cold winter of 2009/2010 can alter the temporal separability pattern significantly. Due to the extensive use of the NDVI for land cover discrimination, the findings of this study should be transferrable to data from other optical sensors. However, the high impact of outliers from the general climatic pattern highlights the limitation of spatial transferability to locations with different climatic and land cover conditions. The use of high-temporal, moderate resolution data such as MODIS in conjunction with machine-learning techniques proved to be a good base for the prediction of image acquisition timing for optimal land cover classification results.2

show abstract

Section: Introductionmentioning

confidence: 99%

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Nitze

Barrett

Cawkwell

2015

International Journal of Applied Earth Observation and Geoinfor

116

View full text Add to dashboard Cite

show abstract

“…The methods exploit both the absolute greenness as well as the greenness dynamics, or land surface phenology, of the disparate crop types (Chang et al 2007;Shao et al 2010;Turker and Arikan 2005;Wardlow, Egbert, and Kastens 2007;Zhong, Gong, and Biging 2014). Data from the MODIS is well suited for mapping crops worldwide because of its daily temporal and moderate spatial resolution (250 m in visible and NIR bands); MODIS data have been used to map crop types across different parts of the world (Teluguntla et al 2017;Vintrou et al 2012;Wardlow and Egbert 2008). There are also studies that combine MODIS data and moderate spatial resolution data, such as Landsat and the Indian Remote Sensing Advanced Wide Field Sensor (AWiFS), to discriminate crop types (Thenkabail and Wu 2012;USDA-NASS 2013).…”

Section: Introductionmentioning

confidence: 99%

Fallow-land Algorithm based on Neighborhood and Temporal Anomalies (FANTA) to map planted versus fallowed croplands using MODIS data to assist in drought studies leading to water and food security assessments

Wallace

Thenkabail

Rodriguez

et al. 2017

GIScience & Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

“…Thus, thematic improvement of global land cover databases is of great importance. There have been ongoing efforts to extend MODIS land cover databases (Biggs et al, 2006;Potgieter et al, 2007;Wardlow et al, 2007;Wardlow and Egbert, 2008;Pittman et al, 2010;He and Bo, 2011;Gumma et al, 2011). For natural vegetation, global high-resolution databases are becoming available (e.g.…”

Section: Discussionmentioning

confidence: 99%

Deriving a per-field land use and land cover map in an agricultural mosaic catchment

Seo

Bogner

Poppenborg

et al. 2014

Earth Syst. Sci. Data

View full text Add to dashboard Cite

Abstract. Detailed data on land use and land cover constitute important information for Earth system models, environmental monitoring and ecosystem services research. Global land cover products are evolving rapidly; however, there is still a lack of information particularly for heterogeneous agricultural landscapes. We censused land use and land cover field by field in the agricultural mosaic catchment Haean in South Korea. We recorded the land cover types with additional information on agricultural practice. In this paper we introduce the data, their collection and the post-processing protocol. Furthermore, because it is important to quantitatively evaluate available land use and land cover products, we compared our data with the MODIS Land Cover Type product (MCD12Q1). During the studied period, a large portion of dry fields was converted to perennial crops. Compared to our data, the forested area was underrepresented and the agricultural area overrepresented in MCD12Q1. In addition, linear landscape elements such as waterbodies were missing in the MODIS product due to its coarse spatial resolution. The data presented here can be useful for earth science and ecosystem services research. The data are available at the public repository Pangaea

show abstract

Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains

Cited by 629 publications

References 46 publications

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Fallow-land Algorithm based on Neighborhood and Temporal Anomalies (FANTA) to map planted versus fallowed croplands using MODIS data to assist in drought studies leading to water and food security assessments

Deriving a per-field land use and land cover map in an agricultural mosaic catchment

Contact Info

Product

Resources

About