A novel classifier for improving wetland mapping by integrating image fusion techniques and ensemble machine learning classifiers

Empowering real-time flood impact assessment through the integration of machine learning and Google Earth Engine: a comprehensive approach

Floods cause substantial losses to life and property, especially in flood-prone regions like northwestern Bangladesh. Timely and precise evaluation of flood impacts is critical for effective flood management and decision-making. This research demonstrates an integrated approach utilizing machine learning and Google Earth Engine to enable real-time flood assessment. Synthetic aperture radar (SAR) data from Sentinel-1 and the Google Earth Engine platform were employed to generate near real-time flood maps of the 2020 flood in Kurigram and Lalmonirhat. An automatic thresholding technique quantified flooded areas. For land use/land cover (LULC) analysis, Sentinel-2's high resolution and machine learning models like artificial neural networks (ANN), random forests (RF) and support vector machines (SVM) were leveraged. ANN delivered the best LULC mapping with 0.94 accuracy based on metrics like accuracy, kappa, mean F1 score, mean sensitivity, mean specificity, mean positive predictive value, mean negative value, mean precision, mean recall, mean detection rate and mean balanced accuracy. Results showed over 600,000 people exposed at peak inundation in July-about 17% of the population. The machine learning-enabled LULC maps reliably identified vulnerable areas to prioritize flood management. Over half of croplands flooded in July. This research demonstrates the potential of integrating SAR, machine learning and cloud computing to empower authorities through real-time monitoring and accurate LULC mapping essential for effective flood response. The proposed comprehensive methodology can assist stakeholders in developing data-driven flood management strategies to reduce impacts.

Research on the extraction method of coastal wetlands based on sentinel-2 data

Wetlands play an important role in ecological health and sustainable development, and dynamic monitoring of their spatial distribution is crucial for developing management and conservation measures. The types of coastal wetlands are complex and diverse, natural and artificial wetlands are easily confused, making precise classification more difficult. The coastal wetland of Chongming Island in China, which has diverse types and unique and complex ecological and hydrological characteristics, was deliberately chosen as a challenging case study. The objective of this study was to research effective method of fine classification of coastal wetlands, by constructing feature variables and proposing strategies for multi-level selection and fusion of feature variables. Sentinel-2 data with rich spectral information and high spatial resolution was be used. In this study, firstly, the classification effect of characteristic variables such as vegetation index, water body index, red edge index, and texture index were evaluated. Focusing on the "different objects with same spectra" of the humid planning land and farm growing ponds, the spectral characteristics of them were analyzed and a "water-rich soil index (WRSI)" was established. Subsequently, correlation analysis and J-M distance method were used to multi-level selection for the feature variables and four sets of features combination schemes were established. Finally, random forest (RF) was applied to classify coastal wetlands using different feature combination schemes, and the accuracy of different schemes was compared and verified. The results show the following: 1)Texture features have a promoting effect on improving classification accuracy. The constructed "water rich soil index"(WRSI) has the effectively contribution to identification and classification of farm growing ponds and humid planned land, improving the overall classification accuracy by 6.52%. 2)By multi-level selecting and fusion of feature variable sets, both accuracy and efficiency for classification are improved. For different features combination schemes, the classification accuracy is up to 90.03% by integrating spectral features, spectral index, texture index, and WRSI. This study evaluates the potential of Sentinel-2 data in coastal wetland classification, constructs effective feature parameters, and provides a new idea for wetland information extraction. The resulting classification map can be used for sustainable management, ecological assessment and conservation of the coastal wetland.

Anthropogenic impacts on urban blue space and its reciprocal effect on human and socio-ecological health

Quantifying anthropogenic impacts on blue space (BS) and its effect on human and socio-ecological health was least explored. The present study aimed to do this in reference to the urban BS transformation scenario of Eastern India. To measure BS transformation, Landsat image-based water indices were run from 1990 to 2021. Anthropogenic impact score (AIS) and 7 components scores of 78 selected BS on 70 parameters related data driven from the field. Total 345 respondents were taken for human and socio-ecological health assessment. For this, depression (DEP), anxiety (ANX), stress (STR), physical activities (PA), social capital (SC), therapeutic landscape (TL) and environment building (EB) parameters were taken. The result exhibited that BS was reduced. About 50% of urban core BS was reported highly impacted. Human and socio-ecological health was identified as good in proximity to BS, but it was observed better in the cases of larger peripheral BS. AIS on BS was found to be positively associated with mental health (0.47-0.63) and negatively associated with PA, SC, TL and EB (-0.50 to -0.90). Standard residual in ordinary least square was reported low (-1.5 to 1.5) in 95% BS. Therefore, BS health restoration and management is crucial for sustaining the living environment.

Socio-Ecological Approach to a Forest-Swamp-Savannah Mosaic Landscape Using Remote Sensing and Local Knowledge: a Case Study in the Bas-Ogooué Ramsar Site, Gabon

Studies of landscape dynamics in protected areas often rely exclusively on remotely-sensed data, leading to bias by neglecting how local inhabitants, who often have a long history of interaction with their environment, perceive and structure the landscape over time. Using a socio-ecological system (SES) approach in a forest-swamp-savannah mosaic within the Bas-Ogooué Ramsar site in Gabon, we assess how human populations participate in landscape dynamics over time. We first conducted a remote sensing analysis to produce a land-cover map representing the biophysical dimension of the SES. This map is based on pixel-oriented classifications, using a 2017 Sentinel-2 satellite image and 610 GPS points, that categorized the landscape in 11 ecological classes. To study the landscape's social dimension, we collected data on local knowledge to understand how local people perceive and use the landscape. These data were collected through 19 semi-structured individual interviews, three focus groups and 3 months of participant observation during an immersive field mission. We developed a systemic approach by combining data on biophysical and social dimensions of the landscape. Our analysis shows that in the absence of continued anthropic interventions, both savannahs and swamps dominated by herbaceous vegetation will experience closure by encroaching woody vegetation, leading to eventual biodiversity loss. Our methodology based on an SES approach to landscapes could improve the conservation programs developed by Ramsar site managers. Designing actions at the local scale, rather than applying one set of actions to the entire protected area, allows the integration of human perceptions, practices and expectations, a challenge that is more than essential in the context of global change.

Mapping small inland wetlands in the South-Kivu province by integrating optical and SAR data with statistical models for accurate distribution assessment

There are several techniques for mapping wetlands. In this study, we examined four statistical models to assess the potential distribution of wetlands in the South-Kivu province by combining optical and SAR images. The approach involved integrating topographic, hydrological, and vegetation indices into the four most used classifiers, namely Artificial Neural Network (ANN), Random Forest (RF), Boosted Regression Tree (BRT), and Maximum Entropy (MaxEnt). A wetland distribution map was generated and classified into 'wetland' and 'non-wetland.' The results showed variations in predictions among the different models. RF exhibited the most accurate predictions, achieving an overall classification accuracy of 95.67% and AUC and TSS values of 82.4%. Integrating SAR data improved accuracy and precision, particularly for mapping small inland wetlands. Our estimations indicate that wetlands cover approximately 13.5% (898,690 ha) of the entire province. BRT estimated wetland areas to be ~ 16% (1,106,080 ha), while ANN estimated ~ 14% (967,820 ha), MaxEnt ~ 15% (1,036,950 ha), and RF approximately ~ 10% (691,300 ha). The distribution of these areas varied across different territories, with higher values observed in Mwenga, Shabunda, and Fizi. Many of these areas are permanently flooded, while others experience seasonal inundation. Through digitization, the delineation process revealed variations in wetland areas, ranging from tens to thousands of hectares. The geographical distribution of wetlands generated in this study will serve as an essential reference for future investigations and pave the way for further research on characterizing and categorizing these areas.

Wetland health assessment using DPSI framework: a case study in Kolkata Metropolitan Area

Wetlands are among the most valuable components of the ecosystem, playing an important role in preventing floods, maintaining the hydrological cycle, protecting against natural hazards, and controlling local weather conditions and ecological restoration. The Kolkata Metropolitan Area (KMA) is considered one of the most ecologically valuable regions in terms of wetland ecosystem, but due to haphazard development and human activities, the wetlands of the city are under constant threat of degradation. Therefore, this study aims to assess the factors responsible for wetland health and their dynamics using Driving Force-Pressure-State-Impact (DPSI) framework. To assess wetland health during 2011-2020, seventeen indicators and four sub-indicators were selected to calculate weights using the analytic hierarchy process (AHP). The results showed that most of the municipalities in the healthy category were in the pressure (P) section in 2011, while fluctuations were observed in the impact (I) section in several wards during 2011-20. The condition section (S) showed the overall change in the water, vegetation, and built-up categories from 2011 to 2020, so the most dominant category was "healthy," followed by "unhealthy" and "poor." The highly significant factors worsening wetland health were population density (B1), road density (B3), per capita wastewater generation (B5), per capita solid waste generation (B7), biological oxygen demand (D1a), dissolved oxygen (D1b), pH (D1c), and total coliform (D1d). The results of the study can help develop sustainable conservation and management of the wetland ecosystem in the KMA urban area and at the global level with similar geographical conditions.

Resolution effects on ox-bow lake mapping and inundation consistency analysis in moribund deltaic flood plain of India

Research on investigating spatial resolution effect on image-based wetland mapping was done, and reported finer resolution is more appropriate. But is Sentinel image more effective than Landsat image for delineating ox-bow lake, a cut-off channel of a river, and for mapping inundation frequency? Inundation frequency means regularly, water appears in a pixel. In order to obtain these answers, the present study used frequently used spectral indices like normalized difference water index (NDWI), modified NDWI (MNDWI), re-modified NDWI (RmNDWI) and ensemble vegetation inclusive aggregated water index (ViAWI). For obtaining inundation consistency character, the water presence frequency (WPF) approach was adopted. A set of accuracy matrices was applied for validating the resolution effect. Results revealed that among the used indices, MNDWI was found suitable for ox-bow lake mapping. But this index is not able to map vegetated part of the ox-bow lakes. This problem was resolved using ensemble ViAWI. Inundation frequency analysis exhibited that about 70% of the area is consistent with water presence and therefore is hydro-ecologically and economically viable, and no such major differences were recorded between Sentinel and Landsat images. The study further revealed that finer resolution Sentinel images are more effective in ox-bow lake mapping and characterising inundation frequency, but they were not significantly better. Accuracy difference between them was found at the very minimum. Therefore, the study recommended that in a Sentinel image sparse condition, Landsat images could alternatively be used without much accuracy departure, particularly on those water bodies where water appearance is not highly erratic.