Mapping Agricultural Landuse Patterns from Time Series of Landsat 8 Using Random Forest Based Hierarchial Approach

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2019-03, Vol.11 (5), p.601
• Main Authors: Pareeth, Sajid, Karimi, Poolad, Shafiei, Mojtaba, De Fraiture, Charlotte
• Format: Article
• Language: English
• Subjects: Agricultural land; Agricultural management; Agricultural production; Agriculture; Algorithms; Arid regions; Arid zones; Classification; Decision making; Decision trees; Food production; Irrigated area; Irrigated lands; Irrigation; Land cover; Land use; Landsat; Landsat 8; Landsat satellites; Landuse; Learning algorithms; Machine learning; Mapping; Mashhad; Monitoring; Monitoring systems; Post-production processing; Productivity; Random Forest; Remote sensing; Semi arid areas; Semiarid lands; Spatial data; Spatial discrimination; Spatial resolution; Studies; Time series; Water resources
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs11050601

Increase in irrigated area, driven by demand for more food production, in the semi-arid regions of Asia and Africa is putting pressure on the already strained available water resources. To cope and manage this situation, monitoring spatial and temporal dynamics of the irrigated area land use at basin level is needed to ensure proper allocation of water. Publicly available satellite data at high spatial resolution and advances in remote sensing techniques offer a viable opportunity. In this study, we developed a new approach using time series of Landsat 8 (L8) data and Random Forest (RF) machine learning algorithm by introducing a hierarchical post-processing scheme to extract key Land Use Land Cover (LULC) types. We implemented this approach for Mashhad basin in Iran to develop a LULC map at 15 m spatial resolution with nine classes for the crop year 2015/2016. In addition, five irrigated land use types were extracted for three crop years—2013/2014, 2014/2015, and 2015/2016—using the RF models. The total irrigated area was estimated at 1796.16 km2, 1581.7 km2 and 1578.26 km2 for the cropping years 2013/2014, 2014/2015 and 2015/2016, respectively. The overall accuracy of the final LULC map was 87.2% with a kappa coefficient of 0.85. The methodology was implemented using open data and open source libraries. The ability of the RF models to extract key LULC types at basin level shows the usability of such approaches for operational near real time monitoring.