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

Abstract

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

Landsat-Based Trend Analysis of Lake Dynamics across Northern Permafrost Regions

“…For the classification process we used a Random Forest (RF) [84] MLC algorithm. This non-parametric method has been established as one of the most accurate and widely used algorithms [85][86][87] for remote sensing and other classification applications because of its robustness, independence of statistical data distributions, and capabilities to work with a wide array of input data types. We selected 568 training samples within and in close proximity to our study sites with respect to a variety of surface conditions, such as permafrost type, geological properties, vegetation types, water color and target classes.…”

Land Cover and Crop Type Classification along the Season Based on Biophysical Variables Retrieved from Multi-Sensor High-Resolution Time Series

“…Amongst the possible alternatives [64][65][66], the mean decrease of the Gini Index (GI) was calculated and stored at each observation (34 dates) and for each classification. To assess the date importance, the random forest turns off one of the acquisition dates and keeps the others constant to evaluate the decline in accuracy using the Gini Index at each node of the random forest [47].…”

Phenology-Based Vegetation Index Differencing for Mapping of Rubber Plantations Using Landsat OLI Data

“…Multi-seasonal imagery that captures different periods of the growing season is of considerable value for characterizing land cover types [18][19][20][21][22][23]. In particular, using paired leaf-on and leaf-off images can result in substantial improvements in the accuracy of classifying forest types [24].…”