Framework for Mapping Integrated Crop-Livestock Systems in Mato Grosso, Brazil

• Main Authors: Víctor Danilo Manabe, Marcio R. S. Melo, Jansle Vieira Rocha
• Format: Article
• Language: English
• Published: MDPI AG 2018-08-01
• Series: Remote Sensing
• Subjects: time series; enhanced vegetation index; land-use intensification; Time-Weighted Dynamic Time Warping (TWDTW); temporal pattern
• Online Access: http://www.mdpi.com/2072-4292/10/9/1322

Integrated crop-livestock (ICL) systems combine livestock and crop production in the same area, increasing the efficiency of land use and machinery, while mitigating greenhouse gas emissions, and reducing production risks, plant diseases and pests. ICL systems are primarily divided into annual (ICLa) and multi-annual (ICLm) systems. Projects such as the “Integrated crop-livestock-forest Network” and the “Livestock Rally” have estimated the ICL areas for Brazil on a state or regional basis. However, it remains necessary to create methods for spatial identification of ICL areas. Thus, we developed a framework for mapping ICL areas in Mato Grosso, Brazil using the Enhanced Vegetation Index time-series of Moderate Resolution Imaging Spectroradiometer and a Time-Weighted Dynamic Time Warping (TWDTW) classification method. The classification of ICL areas occurred in three phases. Phase 1 corresponded to the classification of land use from 2008 to 2016. In Phase 2, the ICLa areas were identified. Finally, Phase 3 corresponded to the ICLm identification. The framework showed overall accuracies of 86% and 92% for ICL areas. ICLm accounted for 87% of the ICL areas. Considering only agricultural areas or only pasture areas, ICL systems represented 5% and 15%, respectively.