Application of Artificial Neural Networks for Mangrove Mapping Using Multi-Temporal and Multi-Source Remote Sensing Imagery

Mangroves, as unique coastal wetlands with numerous benefits, are endangered mainly due to the coupled effects of anthropogenic activities and climate change. Therefore, acquiring reliable and up-to-date information about these ecosystems is vital for their conservation and sustainable blue carbon development. In this regard, the joint use of remote sensing data and machine learning algorithms can assist in producing accurate mangrove ecosystem maps. This study investigated the potential of artificial neural networks (ANNs) with different topologies and specifications for mangrove classification in Iran. To this end, multi-temporal synthetic aperture radar (SAR) and multi-spectral remote sensing data from Sentinel-1 and Sentinel-2 were processed in the Google Earth Engine (GEE) cloud computing platform. Afterward, the ANN topologies and specifications considering the number of layers and neurons, learning algorithm, type of activation function, and learning rate were examined for mangrove ecosystem mapping. The results indicated that an ANN model with four hidden layers, 36 neurons in each layer, adaptive moment estimation (Adam) learning algorithm, rectified linear unit (Relu) activation function, and the learning rate of 0.001 produced the most accurate mangrove ecosystem map (F-score = 0.97). Further analysis revealed that although ANN models were subjected to accuracy decline when a limited number of training samples were used, they still resulted in satisfactory results. Additionally, it was observed that ANN models had a high resistance when training samples included wrong labels, and only the ANN model with the Adam learning algorithm produced an accurate mangrove ecosystem map when no data standardization was performed. Moreover, further investigations showed the higher potential of multi-temporal and multi-source remote sensing data compared to single-source and mono-temporal (e.g., single season) for accurate mangrove ecosystem mapping. Overall, the high potential of the proposed method, along with utilizing open-access satellite images and big-geo data processing platforms (i.e., GEE, Google Colab, and scikit-learn), made the proposed approach efficient and applicable over other study areas for all interested users.

The Stability and Suitability of the Bhasan Char Island as an Accommodation for the Forcibly Displaced Myanmar Nationals (FDMN)

Assessing the dynamics of Bhasan Char is very crucial, as the Government of Bangladesh (GoB) has recently selected the island as the accommodation of the FDMN. This article critically evaluates the spatiotemporal morphological variations due to erosion, accretion, and subsurface deformation of the island through multi-temporal geospatial and geophysical data analysis, groundwater quality-quantity, and also determines the nature and rate of changes from 2003 to 2020. This is the first study in this island on which multi-temporal Landsat Satellite Imagery and seismic data have been used with geospatial techniques with Digital Shoreline Analysis System (DSAS) and petrel platform, respectively. The analysis of satellite images suggests that the island first appeared in 2003 in the Bay of Bengal, then progressively evolved to the present stable condition. Significant changes have taken place in the morphological and geographical conditions of the island since its inception. Since 2012, the island has been constantly accreted by insignificant erosion. It receives tidally influenced fluvial sediments from the Ganges-Brahmaputra-Meghna (GBM) river system and the sedimentary accretion, in this case, is higher than the erosion due to relatively weaker wave action and longshore currents. It has gained approximately 68 km2 area, mostly in the northern part and because of erosion in the south. Although the migration of the Bhasan Char was ubiquitous during 2003–2012, it has been concentrated in a small area to the east since 2018. The net shoreline movements (NSM) suggest that the length of the shoreline enlarged significantly by around 39 km in 2020 from its first appearance. Seismic and GPS data clearly indicate that the island is located on the crest of a slowly uplifting low-amplitude anticline, which may result in a stable landform around the island. Based on the analysis of historical data, it has been assessed that the current configuration of Bhasan Char would not be severely affected by 10–15-foot-high cyclone. Therefore, FDMN rehabilitation here might be safer that would be a good example for future geo-environmental assessment for any areas around the world for rehabilitation of human in remote and vulnerable island. The findings of this research will facilitate the government’s decision to rehabilitate FDMN refugees to the island and also contribute to future research in this area.

Rice Mapping in Training Sample Shortage Regions Using a Deep Semantic Segmentation Model Trained on Pseudo-Labels

A deep semantic segmentation model-based method can achieve state-of-the-art accuracy and high computational efficiency in large-scale crop mapping. However, the model cannot be widely used in actual large-scale crop mapping applications, mainly because the annotation of ground truth data for deep semantic segmentation model training is time-consuming. At the operational level, it is extremely difficult to obtain a large amount of ground reference data by photointerpretation for the model training. Consequently, in order to solve this problem, this study introduces a workflow that aims to extract rice distribution information in training sample shortage regions, using a deep semantic segmentation model (i.e., U-Net) trained on pseudo-labels. Based on the time series Sentinel-1 images, Cropland Data Layer (CDL) and U-Net model, the optimal multi-temporal datasets for rice mapping were summarized, using the global search method. Then, based on the optimal multi-temporal datasets, the proposed workflow (a combination of K-Means and random forest) was directly used to extract the rice-distribution information of Jiangsu (i.e., the K–RF pseudo-labels). For comparison, the optimal well-trained U-Net model acquired from Arkansas (i.e., the transfer model) was also transferred to Jiangsu to extract local rice-distribution information (i.e., the TF pseudo-labels). Finally, the pseudo-labels with high confidences generated from the two methods were further used to retrain the U-Net models, which were suitable for rice mapping in Jiangsu. For different rice planting pattern regions of Jiangsu, the final results showed that, compared with the U-Net model trained on the TF pseudo-labels, the rice area extraction errors of pseudo-labels could be further reduced by using the U-Net model trained on the K–RF pseudo-labels. In addition, compared with the existing rule-based rice mapping methods, he U-Net model trained on the K–RF pseudo-labels could robustly extract the spatial distribution information of rice. Generally, this study could provide new options for applying a deep semantic segmentation model to training sample shortage regions.

Filling and drainage of a subglacial lake beneath the Flade Isblink ice cap, northeast Greenland

The generation, transport, storage and drainage of meltwater beneath the ice sheet play important roles in the Greenland ice sheet (GrIS) system. Active subglacial lakes, common features in Antarctica, have recently been detected beneath GrIS and may impact ice sheet hydrology. Despite their potential importance, few repeat subglacial lake filling and drainage events have been identified under Greenland Ice Sheet. Here we examine the surface elevation change of a collapse basin at the Flade Isblink ice cap, northeast Greenland, which formed due to sudden subglacial lake drainage in 2011. We estimate the subglacial lake volume evolution using multi-temporal ArcticDEM data and ICESat-2 altimetry data acquired between 2012 and 2021. Our long-term observations show that the subglacial lake was continuously filled by surface meltwater, with basin surface rising by up to 55 m during 2012–2021 and we estimate 138.2 × 106 m3 of meltwater was transported into the subglacial lake between 2012 and 2017. A second rapid drainage event occurred in late August 2019, which induced an abrupt ice dynamic response. Comparison between the two drainage events shows that the 2019 drainage released much less water than the 2011 event. We conclude that multiple factors, e.g., the volume of water stored in the subglacial lake and bedrock relief, regulate the episodic filling and drainage of the lake. By comparing the surface meltwater production and the subglacial lake volume change, we find only ~64 % of the surface meltwater successfully descended to the bed, suggesting potential processes such as meltwater refreezing and firn aquifer storage, need to be further quantified.

Genus-Physiognomy-Ecosystem Map with 88 Legends Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images

This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score.

Multi-Temporal InSAR for transport infrastructure monitoring: Recent trends and challenges

Worldwide, transport infrastructure is increasingly vulnerable to ageing-induced deterioration and climate-related hazards. Oftentimes inspection and maintenance costs far exceed available resources, and numerous assets lack any rigorous structural evaluation. Space-borne Synthetic Aperture Radar Interferometry (InSAR) is a powerful remote-sensing technology, which can provide cheaper deformation measurements for bridges and other transport infrastructure with short revisit times, while scaling from the local to the global scale. As recent studies have shown the InSAR accuracy to be comparable with traditional monitoring instruments, InSAR could offer a cost-effective tool for long-term, near-continuous deformation monitoring, with the possibility to support inspection planning and maintenance prioritisation, while maximising functionality and increasing the resilience of infrastructure networks. However, despite the high potential of InSAR for structural monitoring, some important limitations need to be considered when applying it in reality. This paper identifies and discusses the challenges of using InSAR for the purpose of structural monitoring, with a specific focus on bridges and transport networks. Examples are presented to illustrate current practical limitations of InSAR; possible solutions and promising research directions are identified. The aim of this study is to motivate future action in this area and highlight the InSAR advances needed to overcome current challenges.

Multi-temporal runoff-sediment discharge relationships

To understand the runoff-sediment discharge relationship , this study examined the annual runoff and sediment discharge data obtained from the Tangnaihai hydrometric station. The data were decomposed into multiple time scales through Complete Ensemble Empirical Mode Decomposition with adaptive noise (CEEMDAN). Furthermore, double cumulative curves were plotted and the cointegration theory was employed to analyze the microscopic and macroscopic multi-temporal correlations between the runoff and the sediment discharge and their detailed evolution.