Mapping of rice growth phases and bare land using Landsat-8 OLI with machine learning

Regular monitoring and mapping of rice (Oryza Sativa) growth phases are essential for industry stakeholders to ensure food production is on track and to assess the impact of climate change on rice production. In Indonesia, high-cost field surveys have been widely used to monitor the rice growth phases. Alternatively, this research proposes a methodology to retrieve multi-temporal rice phenology (vegetative, reproductive, and ripening) and bare land mapping using medium resolution remote sensing imagery obtained from Landsat-8 Operational Land Imager (OLI) combined with machine learning techniques. In this study, we have used extensive ground validation information collected from 2014 to 2016 for training the models. This ground validation information was obtained from pre-installed webcams across Indonesia. Five different machine learning algorithms were used including random forest (RF), support vector machine (SVM) with three kernel functions (linear, polynomial, and radial) and artificial neural networks (ANN) to classify rice growth phases and bare land. This paper also evaluates the temporal evolution of rice phenology and bare land to check the prediction model consistency between two consecutive dates in 3 years. The results show that the nonlinear SVM algorithm gives the best model accuracy (70.5% with Kappa: 0.66) based on the test dataset and the lowest temporal changes (<11%). Spatial-temporal assessment of rice phenology and bare land from Landsat-8 indicated that the models were reliable and robust over different seasons and years. The distribution of rice phenology maps will enable Indonesian management authorities to supply fertilizer, allocate water resources, harvesting, and marketing facilities more efficiently.