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

Sajid Pareeth,Mojtaba Shafiei,Poolad Karimi,Charlotte De Fraiture

doi:10.3390/rs11050601

Abstract

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.

Highlights

There is an increase in population vulnerable to water scarcity and food security [1,2]
This study focused on developing a Random Forest (RF) based irrigated land use monitoring work flow using time series of Landsat 8 (L8) optical data
Data acquired from the Operational Land Imager (OLI) instrument aboard L8 satellite launched in February 2013 were used in this study

Summary

Introduction

There is an increase in population vulnerable to water scarcity and food security [1,2]. United Nation’s Sustainable Development Goals (SDG) on “Zero hunger” (Goal 2) and “Clean water and sanitation” (Goal 6) target achieving food and water security by increasing agricultural productivity and efficient water use to reduce people susceptible to water scarcity and to feed the increasing population [8]. To improve land and water use efficiency, it is critical to monitor these at different scales, most importantly at a basin scale where water allocation to different sectors takes place [9,10]. Monitoring the spatial extent and temporal dynamics of the irrigated land use would enable managers and policy makers to make timely decisions to achieve higher crop water productivity [12]

Methods

Results

Discussion

Conclusion