Flood hazard potential evaluation using decision tree state-of-the-art models.

Floods occur frequently in Romania and throughout the world and are one of the most devastating natural disasters that impact people's lives. Therefore, in order to reduce the potential damages, an accurate identification of surfaces susceptible to flood phenomena is mandatory. In this regard, the quantitative calculation of flood susceptibility has become a very popular practice in the scientific research. With the development of modern computerized methods such as geographic information system and machine learning models, and as a result of the possibility of combining them, the determination of areas susceptible to floods has become increasingly accurate, and the algorithms used are increasingly varied. Some of the most used and highly accurate machine learning algorithms are the decision tree models. Therefore, in the present study focusing on flood susceptibility zonation mapping in the Trotus River basin, the following algorithms were applied: forest by penalizing attribute-weights of evidence (forest-PA-WOE), best first decision tree-WOE, alternating decision tree-WOE, and logistic regression-WOE. The best performant, characterized by a maximum accuracy of 0.981, proved to be forest-PA-WOE, whereas in terms of flood exposure, an area of over 16.22% of the Trotus basin is exposed to high and very high floods susceptibility. The performances applied models in the present work are higher than the models applied in the previous studies in the same study area. Moreover, it should be noted that the accuracy of the models is similar with the accuracies of the decision tree models achieved in the studies focused on other areas across the world. Therefore, we can state that the models applied in the present research can be successfully used in by the researchers in other case studies. The findings of this research may substantially map the flood risk areas and further aid watershed managers in limiting and remediating flood damage in the data-scarce regions. Moreover, the results of this study can be a very useful for the hazard management and planning authorities.

Retraction Note: Weather indicators and improving air quality in association with COVID-19 pandemic in India.

[This retracts the article DOI: 10.1007/s00500-021-06012-9.].

Wetland health, water quality, and resident perceptions of declining ecosystem services: a case study of Mount Abu, Rajasthan, India.

Ecosystem services provided by wetlands are essential for communities living near wetlands, especially in an underdeveloped semi-arid landscape. The land use land cover changes and ecosystem degradation and water quality change over the past few decades have had immense effects on declining wetland ecosystem services. With the degradation, it is exerting superfluous effects on wetland communities including loss of livelihood, and decline in other wetland services like fishing, aquaculture, fuelwood, fodder, and many more. The present study attempts to assess the changing nature of wetland health, water quality, and declining ecosystem services of Mount Abu wetlands in Rajasthan, India. For assessing the change of wetland extent, we have used the remote sensing-based data for preparation of land use land cover change from 1992 to 2020. The water samples have been collected from the wetland, and different biophysical parameters of the water have been tested in the laboratory. A questionnaire-based household survey has been conducted to understand the perception of the wetland communities on the loss of ecosystem services over three decades. Further, a correlation and cluster assessment has been conducted to understand the degradation of wetland health in the selected wetlands. The study results indicated deteriorating conditions of wetland health and declining ecosystem services in the study area over the time periods. The land use land cover change analysis indicated a decrease in the spatial extent of the wetlands in the study area. Wetland communities are being affected due to the degradation of wetland health. The study recommended executing a wetland management plan for long-term conservation and livelihood management for the Mount Abu wetlands and communities.

Comparing Delphi-fuzzy AHP and fuzzy logic membership in soil fertility assessment: a study of an active Ganga Delta in Sundarban Biosphere Reserve, India.

The present study led to setting up a grid-based soil fertility map along with the best fit model in the coastal regions based on soil physical (coarse, sand, silt, clay, bulk density), chemical (CEC, pH, and soil organic carbon), topographic (elevation), and nutrient elements (P2O5, K2O, Na, Zn, B) in the active Ganga deltaic region of Sundarban Biosphere Reserve, India. Soil samples have been collected from 30 soil grids, and 0-15 cm soil depth was preferred for fertility analysis because most essential soil chemical and nutrient elements affecting soil fertility are concentrated in this depth range. We have used the fuzzy-AHP-Delphi (FAHP) and fuzzy logic-Delphi (FL) methods to determine the soil fertility zone. The rules are generated on the MATLAB interface in the text form; the words "IF," "THEN," "IS," "AND," etc., are used to complete the mode-building process. The weights and the desirable limits for each criterion were set based on the expert opinions and existing literature. The kriging interpolation method and natural break classification were used to represent the soil fertility maps into five classes, namely very high fertility (0.80-1.0), high fertility (0.60-0.80), moderate fertility (0.40-0.60), low fertility (0.20-0.40), and very low fertility (0.00-0.20) respectively. Both the models show that soil fertility is respectively higher near the Hooghly River bank. In many cases, the results obtained from FAHP and FL are quite similar but huge dissimilarity has been noticed in grid numbers G2, G3, G4, F1, and F2. Since the FAHP method has been used for the weight of each criterion, therefore, it only prefers those more important parameters over others. The overall accuracy of the soil fertility map was 82.16% for the fuzzy logic model, and 79.62% for the FAHP model and the kappa coefficient value was determined as 0.82 for the fuzzy logic model and 0.79 for the FAHP model. The soil fertility map was validated using the success rate curve under the ROC technique, and the area under curve (AUC) was calculated as 84.02% for the fuzzy logic model and 81.60% for the FAHP model. Since the standard limits for each criterion were known, therefore, fuzzy logic was found to best fit the model for analyzing soil fertility for each grid.

Weather indicators and improving air quality in association with COVID-19 pandemic in India.

The COVID-19 pandemic enforced nationwide lockdown, which has restricted human activities from March 24 to May 3, 2020, resulted in an improved air quality across India. The present research investigates the connection between COVID-19 pandemic-imposed lockdown and its relation to the present air quality in India; besides, relationship between climate variables and daily new affected cases of Coronavirus and mortality in India during the this period has also been examined. The selected seven air quality pollutant parameters (PM10, PM2.5, CO, NO2, SO2, NH3, and O3) at 223 monitoring stations and temperature recorded in New Delhi were used to investigate the spatial pattern of air quality throughout the lockdown. The results showed that the air quality has improved across the country and average temperature and maximum temperature were connected to the outbreak of the COVID-19 pandemic. This outcomes indicates that there is no such relation between climatic parameters and outbreak and its associated mortality. This study will assist the policy maker, researcher, urban planner, and health expert to make suitable strategies against the spreading of COVID-19 in India and abroad. Supplementary Information: The online version contains supplementary material available at 10.1007/s00500-021-06012-9.

Assessment of suitable habitat of mangrove species for prioritizing restoration in coastal ecosystem of Sundarban Biosphere Reserve, India.

Mangrove forests being the abode of diverse fauna and flora are vital for healthy coastal ecosystems. These forests act as a carbon sequester and protection shield against floods, storms, and cyclones. The mangroves of the Sundarban Biosphere Reserve (SBR), being one of the most dynamic and productive ecosystems in the world are in constant degradation. Hence, habitat suitability assessment of mangrove species is of paramount significance for its restoration and ecological benefits. The study aims to assess and prioritize restoration targets for 18 true mangrove species using 10 machine-learning algorithm-based habitat suitability models in the SBR. We identified the degraded mangrove areas between 1975 and 2020 by using Landsat images and field verification. The reserve was divided into 5609 grids using 1 km gird size for understanding the nature of mangrove degradation and collection of species occurrence data. A total of 36 parameters covering physical, environmental, soil, water, bio-climatic and disturbance aspects were chosen for habitat suitability assessment. Niche overlay function and grid-based habitat suitability classes were used to identify the species-based restoration prioritize grids. Habitat suitability analysis revealed that nearly half of the grids are highly suitable for mangrove habitat in the Reserve. Restoration within highly suitable mangrove grids could be achieved in the areas covered with less than 75 percent mangroves and lesser anthropogenic disturbance. The study calls for devising effective management strategies for monitoring and conserving the degraded mangrove cover. Monitoring and effective management strategies can help in maintaining and conserving the degraded mangrove cover. The model proves to be useful for assessing site suitability for restoring mangroves. The other geographical regions interested in assessing habitat suitability and prioritizing the restoration of mangroves may find the methodology adopted in this study effective.

Flood susceptibility evaluation through deep learning optimizer ensembles and GIS techniques.

It is difficult to predict and model with an accurate model the floods, that are one of the most destructive risks across the earth's surface. The main objective of this research is to show the prediction power of three ensemble algorithms with respect to flood susceptibility estimation. These algorithms are: Iterative Classifier Optimizer - Alternating Decision Tree - Frequency Ratio (ICO-ADT-FR), Iterative Classifier Optimizer - Deep Learning Neural Network - Frequency Ratio (ICO-DLNN-FR) and Iterative Classifier Optimizer - Multilayer Perceptron - Frequency Ratio (ICO-MLP-FR). The first stage of the manuscript consisted of the collection and processing of the geodatabase needed in the present study. The geodatabase comprises a number of 14 flood predictors and 132 known flood locations. The Correlation-based Feature Selection (CFS) method was used in order to assess the prediction capacity of the 14 predictors in terms of flood susceptibility estimation. The training and validation of the three ensemble models constitute the next stage of the scientific workflow. Several statistical metrics and ROC curve method were involved in the evaluation of the model's performance and accuracy. According to ROC curves all the models achieved high performances since their AUC had values above 0.89. ICO-DLNN-FR proved to be the most accurate model (AUC = 0.959). The outcomes of the study can be used to guide future flood risk management and sustainable land-use planning in the designated area.

Plastic waste footprint in the context of COVID-19: Reduction challenges and policy recommendations towards sustainable development goals.

The sudden surge in demand to use plastic products due to COVID-19 pandemic has increased plastic pollution. It has resulted into degradation of a broad range of habitats and ecosystems by destroying natural functions, water quality, and environmental sustainability. However, the government agencies, scientific communities, and the public, have started to give attention to this issue. So, in the present study, we used the correlation methods to check the relationship between COVID-19 affected population with the medical plastic waste (MPW) that has developed a conceptual model of the inter-linkages between the preventive measures of COVID-19 pandemic problems and the reduction challenges of plastic waste during and after pandemic scenarios. Emerging issues in the waste management during and after the COVID-19 are established by reviewing the literature, reports, policy briefs, and information from the website concerning COVID-19. Considering MPW management issues, we selected India as a case study to analyse the plastic waste footprint (PWF) due to COVID-19 pandemic. The correlation results showed COVID-19 affected population and MPW; COVID-19 affected population and PWF have a significant relationship (R2 = 0.60; Area under ROC curve 81.4%). It suggests an urgent need for plastic waste management initiatives. Moreover, substantial plastic products, human awareness, strict government regulations, and inclusive research can check plastic waste footprints in India and worldwide. Then discuss the specific pathways through which the immediate and long-term impacts operate and highlight the issues of hampering the sustainable development goals (SDGs) progress in India and beyond. Finally, call for coordinated assessment, support and appropriate short- and long-term mitigation and the policy measures of plastic waste problems during and after the COVID-19 pandemic.

Evaluation of different boosting ensemble machine learning models and novel deep learning and boosting framework for head-cut gully erosion susceptibility.

The objective of this study is to assess the gully head-cut erosion susceptibility and identify gully erosion prone areas in the Meimand watershed, Iran. In recent years, this study area has been greatly influenced by several head-cut gullies due to unusual climatic factors and human induced activity. The present study is therefore intended to address this issue by developing head-cut gully erosion prediction maps using boosting ensemble machine learning algorithms, namely Boosted Tree (BT), Boosted Generalized Linear Models (BGLM), Boosted Regression Tree (BRT), Extreme Gradient Boosting (XGB), and Deep Boost (DB). Initially, we produced a gully erosion inventory map using a variety of resources, including published reports, Google Earth images, and field records of the Global Positioning System (GPS). Subsequently, we distributed this information randomly and choose 70% (102) of the test gullies and the remaining 30% (43) for validation. The methodology was designed using morphometric and thematic determinants, including 14 head-cut gully erosion conditioning features. We have also investigated the following: (a) Multi-collinearity analysis to determine the linearity of the independent variables, (b) Predictive capability of piping models using train and test dataset and (c) Variables importance affecting head-cut gully erosion. The study reveals that altitude, land use, distances from road and soil characteristics influenced the method with the greatest impact on head-cut gully erosion susceptibility. We presented five head-cut gully erosion susceptibility maps and investigated their predictive accuracy through area under curve (AUC). The AUC test reveals that the DB machine learning method demonstrated significantly higher accuracy (AUC = 0.95) than the BT (AUC = 0.93), BGLM (AUC = 0.91), BRT (AUC = 0.94) and XGB (AUC = 0.92) approaches. The predicted head-cut gully erosion susceptibility maps can be used by policy makers and local authorities for soil conservation and to prevent threats to human activities.

A district-level susceptibility and vulnerability assessment of the COVID-19 pandemic's footprint in India.

In this study, we trace the COVID-19 pandemic's footprint across India's districts. We identify its primary epicentres and the outbreak's imprint in India's hinterlands in four separate time-steps, signifying the different lockdown stages. We also identify hotspots and predict areas where the pandemic may spread next. Significant clusters in the country's western and northern parts pose risk, along with the threat of rising numbers in the east. We also perform epidemiological and socioeconomic susceptibility and vulnerability analyses, identifying resident populations that may be physiologically weaker, leading to a high incidence of cases and pinpoint regions that may report high fatalities due to ambient poor demographic and health-related factors. Districts with a high share of urban population and high population density face elevated COVID-19 risks. Aspirational districts have a higher magnitude of transmission and fatality. Discerning such locations can allow targeted resource allocation to combat the pandemic's next phase in India.

A systematic review on high conservation value assessment (HCVs): Challenges and framework for future research on conservation strategy.

Various scholars and research institutions have attempted to assess High Conservation Values (HCVs) using different methodologies and approaches. Various countries have developed toolkits to determine High Conservation Value Areas (HCVAs) according to their needs and conservation strategies but there is no global agreement on them. The present study attempts to review research papers and assessment reports from 1999 until 2018 on approaches and methodologies used for HCVs all over the world and provide a review into HCV research systematically, with due consideration to the linkages between Biodiversity, Ecosystem Services and Socio-Economic-Cultural values. We analyzed and examined the trends which are emerging and gaps present in HCV assessments evident from literature reviewed by experts, including the spatial spread of research, the evolving use and content of the concept, and consultation with stakeholders. A total, 80 articles were taken from Scopus and various reputed journals and reports using keywords like HCV and Forest Stewardship Council (FSC) to specifically focus on the application and evolution of the concept designed by FSC. The study was done in the hope to help in analyzing different HCV components as a conservation planning tool and guide new research in methodologies to fill the current gaps and enhance HCV assessments at different levels of application. The review result revealed that the HCV approach is an effective tool for delineating the conservation priority areas and reduce the uncontrolled extraction of natural resources. The findings display the focus area in HCV research that are surveying methods, fields of application and the dynamics between social and environmental components of HCV categories.

Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan.

Landslides represent a part of the cascade of geological hazards in a wide range of geo-environments. In this study, we aim to investigate and compare the performance of two state-of-the-art machine learning models, i.e., decision tree (DT) and random forest (RF) approaches to model the massive rainfall-triggered landslide occurrences in the Izu-Oshima Volcanic Island, Japan at a regional scale. At first, a landslide inventory map is prepared consisting of 44 landslide polygons (10,444 pixels) from aerial photo-interpretation and field surveys. To estimate the robustness of the models, we randomly adapted two different samples (S1 and S2), comprising of both positive and negative cells (70% of total landslides - 7293 pixels) for training and remaining (30%-3151 pixels) for validation. Twelve causative factors including altitude, slope angle, slope aspect, plan curvature, total curvature, compound topographic index, stream power index, distance to drainage network, drainage density, distance to geological boundaries, lithology and cumulative rainfall were selected as predictors to implement the landslide susceptibility model. The area under the receiver operating characteristics (ROC) curves (AUC) and other statistical signifiers were used to verify the model accuracies. The result shows that the DT and RF models achieved remarkable predictive performance (AUC > 0.9), producing near accurate susceptibility maps. The overall efficiency of RF (AUC = 0.956) is found significantly higher than the DT (AUC = 0.928) results. Additionally, we noticed that the performance of RF for modeling landslide susceptibility is very robust even though the training and validation samples are altered. Considering the performances, we suggest that both RF and DT models can be used in other similar non-eruption-related landslide studies in the tephra-deposited rich volcanoes, as they are capable of rapidly generating accurate and stable LSM maps for risk mitigation, management practices, and decision-making. Moreover, the RF-based model is promising and enough to be recommended as a method to map regional landslide susceptibility.

Analyzing urban spatial patterns and trend of urban growth using urban sprawl matrix: A study on Kolkata urban agglomeration, India.

This research paper analyzed urban spatial pattern and trend of urban growth in Kolkata urban agglomeration, India using urban sprawl matrix during 1990-2000 & 2000-2015. Seven urban classes viz. urban primary core, urban secondary core, sub urban fringe, scatter settlement, urban open space, non-urban area and water body were chosen for analyzing the magnitude and direction of urban expansion. Landsat TM and Landsat 8 OLI satellite data for 1990, 2000 and 2015 were used for assessing land use land cover change, urban land transformation, urban spatial pattern and trend in urban growth. The study revealed that the built up area has increased drastically. This increase in built up area is attributed to decrease in prime agricultural land and open space. The land use/land cover change matrix showed that built up area has expanded by 16.6% during 1990-2000 and 24.5% during 2000-2015. The urban expansion is a result of large share of land transformation from agricultural land at the rate of 153.1% during 1990-2000 and 66.9% during 2000-2015. Analysis of trend of urban growth in 38 municipalities and 3 municipal corporations of Kolkata urban agglomeration revealed that municipalities located along the east bank of river Hooghly and surrounded by Kolkata Municipal Corporation have experienced a very fast urban growth. Urban primary and secondary cores have increased in newly developed municipalities. Sub urban fringe has increased in the municipalities located away from river Hooghly while open space has decreased in all the old municipalities. Pattern of land transformation and trend of urban growth of Kolkata urban agglomeration for the last 25years may help in guiding future planning and policy-making for the urban agglomeration. Integrated approach of remote sensing, GIS and urban sprawl matrix has proved instrumental in analyzing urban expansion and identifying priority areas for effectives planning and management.

Assessing deforestation susceptibility to forest ecosystem in Rudraprayag district, India using fragmentation approach and frequency ratio model.

This study aimed to model deforestation susceptibility in forest ecosystem of Rudraprayag district, India. For this purpose, site-specific physical (slope angle, slope aspect, altitude, annual average rainfall, soil texture, soil depth), and anthropogenic (population distribution, distance from road, distance from settlement, proximity to agricultural land) deforestation conditioning factors were chosen. Landsat TM and OLI images for 1990 and 2015 were utilized to evaluate the changes in forest cover. The frequency ratio model was used for deforestation susceptibility mapping. The extent of deforestation was examined by overlaying forest fragmentation map and deforestation susceptibility map. The results showed that about 112.5km2 forest area has been deforested over the last 25years. Of the total existing forest, nearly 10% area falls under very high, 17% under high and 30% under moderate deforestation susceptibility categories. Patch, edge and perforated have influenced high (64%) and very high (81%) deforestation susceptibility zones. The integrated methodology involving frequency ratio model, fragmentation approach and remote sensing and GIS techniques has proved useful in analyzing deforestation susceptibility and identifying its causative factors. Thus, the methodology adopted in this study can best be utilized for effective planning and management of forest ecosystem.