A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM)

Abstract

Sentinel-2 images are expected to improve global crop monitoring even in challenging tropical small agricultural systems that are characterized by high intra-and inter-field spatial variability and where satellite observations are disturbed by the presence of clouds. To overcome these constraints, we analyzed and optimized the performance of a combined Random Forest (RF) classifier/object-based approach and applied it to multisource satellite data to produce land use maps of a smallholder agricultural zone in Madagascar at five different nomenclature levels. The RF classifier was first optimized by reducing the number of input variables. Experiments were then carried out to (i) test cropland masking prior to the classification of more detailed nomenclature levels, (ii) analyze the importance of each data source (a high spatial resolution (HSR) time series, a very high spatial resolution (VHSR) coverage and a digital elevation model (DEM)) and data type (spectral, textural or other), and (iii) quantify their contributions to classification accuracy levels. The results show that RF classifier optimization allowed for a reduction in the number of variables by 1.5-to 6-fold (depending on the classification level) and thus a reduction in the data processing time. Classification results were improved via the hierarchical approach at all classification levels, achieving an overall accuracy of 91.7% and 64.4% for the cropland and crop subclass levels, respectively. Spectral variables derived from an HSR time series were shown to be the most discriminating, with a better score for spectral indices over the reflectances. VHSR data were only found to be essential when implementing the segmentation of the area into objects and not for the spectral or textural features they can provide during classification.

$M^3\text{Fusion}$: A Deep Learning Architecture for Multiscale Multimodal Multitemporal Satellite Data Fusion

“…Typically, the approaches that use these two types of information [5], [6], perform data fusion at descriptor level [3]. This type of fusion involves extracting a set of independent features for each data source (time series, VHSR image) and then stacking these features together to feed a traditional supervised learning method (i. e., Random Forest).…”

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

“…These new missions revisit the same area more frequently (every four or ten days) [23,24]. These data's fine spatial resolution, global coverage and relatively fine temporal resolution make them of great utility for mapping crop distribution [25,26]. In fact, such high spatial resolution time series with multiple bands and possible derivations contribute large volumes of data that present significant challenges for in-season crop mapping.…”

“…Therefore, the performance of a combination of RF approaches with object-based image analysis for crop mapping has garnered much attention [25,41,42]. However, few studies have paid much attention to producing the early seasonal crop type maps for decision-maker management and mapping crop seasonal dynamics based on new "two high resolution" satellite data.…”

Remote Sensing and Cropping Practices: A Review

“…Combining seasonal optical time series at coarse and moderate resolutions, with an annual VHSR image, improves the accuracy of the classification products [104]. Likewise, with increasing availability of combined optical and radar remote sensing data, research capitalizing the complementarity of both information sources should gain considerable momentum [210].…”

“…These methods are maybe the most accurate, but are the least efficient in terms of time and human resources. Consequently, automated classification approaches were developed, including unsupervised classification [101], single or multi-stage supervised classification [102], decision tree [103], and supervised learning models such as Random Forest or Support Vector Machines [104,105]. Furthermore, Li et al [106] showed that the object-based image analysis (OBIA) approach applied to Landsat, which allowed the use of information about the geometry and topology of the fields, was useful for discriminating irrigated fields.…”