Monitoring of an Indonesian Tropical Wetland by Machine Learning-Based Data Fusion of Passive and Active Microwave Sensors

Abstract

In this study, a novel data fusion approach was used to monitor the water-body extent in a tropical wetland (Lake Sentarum, Indonesia). Monitoring is required in the region to support the conservation of water resources and biodiversity. The developed approach, random forest database unmixing (RFDBUX), makes use of pixel-based random forest regression to overcome the limitations of the existing lookup-table-based approach (DBUX). The RFDBUX approach with passive microwave data (AMSR2) and active microwave data (PALSAR-2) was used from 2012 to 2017 in order to obtain PALSAR-2-like images with a 100 m spatial resolution and three-day temporal resolution. In addition, a thresholding approach for the obtained PALSAR-2-like backscatter coefficient images provided water body extent maps. The validation revealed that the spatial patterns of the images predicted by RFDBUX are consistent with the original PALSAR-2 backscatter coefficient images (r = 0.94, RMSE = 1.04 in average), and that the temporal pattern of the predicted water body extent can track the wetland dynamics. The PALSAR-2-like images should be a useful basis for further investigation of the hydrological/climatological features of the site, and the proposed approach appears to have the potential for application in other tropical regions worldwide. and growth of the neighboring countries of Indonesia. This development policy has resulted in rapid population growth and large changes in land use and land cover in the watershed, which may impact the water quality and dynamics of it [4].Geographical information is needed regarding the lake area to support the conservation of water resources and biodiversity. This is especially important for identifying the water-body dynamics, because during the dry season, the volume of water is very small and found only in the main river, soil basins, and oxbow lakes. During the rainy season, the water overflows inundated areas, lakes, puddles, and river courses. This annual inundation increases the variety of habitats available to the aquatic organisms [5]. In addition to local factors, the amount of lake water is strongly affected by global climate variability and events. For example, the lake becomes extremely dry in the El Niño years [6]. This means that the water-extent variability is controlled by both seasonal changes and the far less predictable annual changes. Even though long-term, frequent, and detailed mapping of the lake water extent is desirable and needed, few studies have attempted it.Satellite remote sensing is suitable for such a purpose. In fact, many techniques for monitoring wetlands have been proposed and developed [7]. In particular, microwave remote sensing is frequently used because it has two advantages, a high sensitivity to surface water instead of liquid water on the ground and observational capability, even under cloud cover or at night.One of the main microwave remote sensing approaches involves the use of synthetic aperture radar (SAR). The backscatter coefficient images derived from SAR can dis...

Spatiotemporal Image Fusion in Remote Sensing

“…Image fusion can be performed at pixel-level, feature-level (e.g., land-cover classes of interest), and decision-level (e.g., purpose driven) [5,11] by considering the following image blending scenarios: (1) combining high and low-spatial resolution images from the same satellite system, e.g., 15 m panchromatic images with 30 multispectral images from Landsat satellite, or from different satellite systems, e.g., SPOT 10 m panchromatic with Landsat multispectral images at 30 m spatial resolution [22]; (2) combining optical and microwave remote sensing images [17,[23][24][25][26][27][28][29]; (3) combining multispectral satellite imagery and Light Detection and Ranging (LiDAR) data [30]; (4) combining multispectral satellite imagery and hyperspectral data [31], (5) combining high-resolution, low-frequency images with low resolution, high-frequency images [32] and (6) fusing microwave (passive) and microwave (active) sensors [33].…”

“…When the application required, calculation of indices before spatiotemporal fusion is performed [40]. low-frequency images with low resolution, high-frequency images [32] and (6) fusing microwave (passive) and microwave (active) sensors [33]. Long revisit time is not suitable for seasonal vegetation phenology monitoring or rapid surface changes.…”

Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks

“…The trained random forest could predict MODIS-like images from the low-resolution images, even when the original MODIS was not obtained owing to cloud cover or lack of observation for other reasons. Popular ML methods such as the random forest [28] and support vector machine [54] techniques have been applied for downscaling satellite-driven data and have shown robust performance; however, the predicted maps tended to show lower variation ranges than the original datasets. This feature is often observed in data-fusion approaches, rendering the effective tracking of abrupt changes or extreme phenomena difficult [55,56].…”

“…However, empirical approaches using machine learning (ML) have been used for a flexible fusion of datasets with highly different features [28,29]. The fundamental process involves ML training with matched pairs between different types of data and then using the training results to predict spatially high-resolution but temporally low-resolution data from counterpart data (temporally high-resolution but spatially low-resolution).…”

Development of an Operational Algorithm for Automated Deforestation Mapping via the Bayesian Integration of Long-Term Optical and Microwave Satellite Data

“…An appropriately tuned constraint enabled us to mitigate errors ( Figure 5), thereby contributing to the robustness of the overall algorithm. The BULC-based sensor fusion also overcame the limitation of the approach by Mizuochi et al [24,25] because it is not dependent on any past match-ups but is the best-effort update of land cover using the Bayesian framework.…”