Search

The information on land use/land cover (LULC) is indispensable in regional planning, policy formulation and tracking land use/land cover changes (LULCC). The rapid urbanization of hilly terrains, driven by population growth, has significant implications for landslide risk reduction. Recognizing the need for an innovative approach for extracting LULC information, the present study uses a random forest (RF) classifier to develop a novel, pre-trained and universal tool that automatically generates LULC classification maps based on natural colour satellite imagery without any training input from the end-user. The proposed framework with an overall accuracy of 0.75 and an area under the curve (AUC) score of 0.95 in the receiver operating characteristic curve (ROC) approach was used for mapping built-up area expansion in regions susceptible to rainfall-induced landslides in Idukki block panchayat (administrative division), Kerala, India. By comparing the LULC information for the years 2012 and 2022, it was understood that the built-up area in the location has increased from 12.76% of the total area in 2012 to 26.48% in 2022. It is important to consider the rapid increase in built-up area expansion in the 'very high' landslide susceptibility zones in the study area. This clearly demonstrates the need for hazard inclusive planning and tracking of LULCC, for disaster risk reduction. Research Highlights: A pre-trained Land Use/Land Cover (LULC) classification tool is developed using the Random Forest (RF) classifier. Based on natural colour satellite imagery, the tool automatically generates LULC maps for various landscapes worldwide. The tool demonstrates a satisfactory performance, achieving an overall accuracy of 0.75 and an overall ROC AUC score of 0.95. The tool was used to understand the LULC changes in Idukki block panchayat between 2012 and 2022. [ABSTRACT FROM AUTHOR]

Introduction: The Indian Himalayas' susceptibility to landslides, particularly as a location where climate change effects may be event catalysts, necessitates the development of dependable landslide susceptibility maps (LSM). Method: This study diverges from traditional binary classification models, framing LSM as a positive-unlabeled learning problem. This approach acknowledges that regions without recorded landslides are not necessarily at low risk but could simply have not experienced landslides yet. The study utilizes novel positive-unlabeled learning-enhanced algorithms—Random Forest, K-Nearest Neighbor, and Decision Tree—to create LSM for Chamoli district, India. Eleven causative factors for landslides are identified, including elevation, aspect, slope, geology, geomorphology, distance to lineament, lithology, NDVI, distance to river, distance to road and residential land use. To address spatial correlation biases, instead of randomly splitting the dataset, the study adopts spatial splitting to get the training and testing datasets. Conclusion: The study reveals that positive-unlabeled learning substantially improves the Area Under Curve and recall, leading to a more conservative LSM compared to binary classification methods. Analysis shows that the southern region of Chamoli exhibits high recall but lower accuracy, suggesting a latent high landslide susceptibility despite a lack of historical landslides in this region. The study also quantifies the impact of human activity on landslide risk, indicating an elevated threat to life and the local economy, especially in Chamoli's southwestern areas. [ABSTRACT FROM AUTHOR]

Accurate forecasting of daily evapotranspiration (ET) is essential for enhancing real-time irrigation scheduling and informed decision-making in water resources allocation. This study investigates the intricate relationships between meteorological variables and evapotranspiration (ET) to enhance the accuracy of ET estimation models. Robust correlations were identified, emphasizing the significance of net radiation (Rn) in predicting ET. The study explores three distinct scenarios, incorporating different combinations of weather variables as input. The first scenario incorporates all weather variables, including date and time, as inputs for model development. The second scenario utilizes only Rn as input to predict ET values. In the third and final scenario, all weather variables, along with date and time, are employed as inputs for comprehensive model development. The multivariate linear regression (MLR) model demonstrated exceptional performance when exclusively using Rn, achieving an impressive R2 value of 0.99 in both calibration and validation phases. However, limitations were observed when Rn was excluded, highlighting the necessity of a comprehensive set of input data. Penalized regression models, including ridge regression, LASSO, and ELNET, exhibited improved performance with the inclusion of Rn, supporting the importance of this variable in refining ET estimates. Machine learning models displayed remarkable performance, with most achieving R2 values exceeding 0.95 in scenarios involving extensive input data. The Support Vector Regression (SVR) model faced challenges, indicating potential overfitting in certain scenarios. In scenarios with limited input data, machine learning models exhibited varying performance, with the Random Forest (RF) model emerging as the most robust model with R2 value of 0.99 and 0.84 during the calibration and validation, respectively. [ABSTRACT FROM AUTHOR]

Electronic waste (e-waste) is considered a major issue that our world is tackling nowadays. This electronic waste causes various health issues to animals as well as human beings which further results in environmental pollution in developing countries like India. To overcome these issues, proper e-waste collection is proposed by using the dynamic sine cosine-based neural network optimization (DSCNN) approach. The major objective of this approach involves collecting waste from the individual, hence handling the widespread adoption and use of smartphones. To enhance waste planning collection, residents upload a photograph of their waste to the waste collection company's server, which mechanically recognizes and categorizes the image. A new classification and detection scheme using the DSCNN approach is proposed for efficient e-waste collection planning and correctly detects the type and quantity of waste components in images. The identification and classification accuracy of the uploaded images is very accurate; this method describes the e-waste collection process in various streets and buildings in Maharashtra, India. Experimental results describe that the proposed approach readily achieves the proper allocation of vehicle collection, vehicle routing plan, and household e-waste collection, resulting in reduced collection costs. Moreover, the proposed DSCNN method is compared to various other methods like random forest algorithm (RFA), fractional henry gas optimization (FHGO), behavior-based swarm model by the fuzzy controller (BSFC), and deep learning convolutional neural network (DL-CNN). The DSCNN approach yielded an e-waste collection detection accuracy of 97%. The accuracy rates of 94%, 95%, 93%, and 92.15% are obtained from the DL-CNN, FHGO, BSFC, and RFA. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Snow cover information is essential for pursuing seasonal variation studies in Himalayan river basins. This study aims to investigate the seasonal variation of snow cover in the Sutlej river basin (Tibet to Bhakra dam in India) over three different seasons: Monsoon (June–September), winter (October-January), and summer (February-May) during the period 2010–2021. Landsat 7 and 8 Surface Reflectance (SR) data is used to develop 108 land use land cover (LULC) maps for 12 years, with three seasons per year and three machine-learning models. The study has conducted on the Google Earth Engine (GEE) platform, employing Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machine (SVM) models to classify the Landsat satellite data and assess the seasonal snow cover variation during the three seasons. The results show that among the three machine learning models, the RF model exhibits the highest average overall accuracy at 98.75%, followed by the CART model at 98.10%, and the SVM model with the lowest accuracy at 97.15%. In terms of snow cover area variability; there is a decline trend in summer snow cover and an increase in monsoon snow cover over the past three years (2019–2021). However, an increasing trend emerges when considering the decadal changes in all three seasons. In addition, the maximum percentages of snow cover area observed as 67.61%, 46.78%, and 30.58% in the summer period of 2013, the winter period of 2019, and the monsoon period of 2021, respectively. Similarly, the minimum percentage of snow cover is 23.22%, 11.36%, and 13.01%, observed in the summer period of 2014, the winter period of 2011, and the monsoon period of 2012, respectively. A comprehensive assessment procedure on temporal and seasonal snow cover variation in a large river basin have been presented in this work, which will help to plan and manage the sustainable water resources in study region. [ABSTRACT FROM AUTHOR]

In present study, the variability in wintertime maximum (Tmax) and minimum (Tmin) temperature patterns over India using observed and deep learning techniques have been assessed. The analysis has been caried out for the period 1979–2018 during the months from November to February. The month of February depicted strongest variability in Tmax and Tmin over Northwest India (NWI) with significant + ve trend for upper half of the country. Wintertime temperature variability was seen to be dominant in the Indo-Gangetic plain area covering some parts of NWI and Northeast India (NEI) for Tmax and Tmin. Also, a gradual increase in the spatial coverage, engulfing majority of South Peninsular India (SPI) and Central India (CI) of the rising Diurnal Temperature Range (DTR) was found from November to January. Decreasing DTR was observed only for January extending along Indo-Gangetic plains. The model Random Forest (RF) performed quite well relative to Long Short-Term Memory model (LSTM) in predicting the winter temperatures (especially for Tmax) during all the considered months. The RF made a robust Tmax forecast during NDJF over all India (RMSE – 0.51, MAPE – 1.4). However, its performance is not up to the mark during the month of February over NEI (RMSE – 1.63, MAPE – 4.5). The maximum fluctuating patterns of temperature have been found during the month of February. The study emphasizes on algorithm-based approaches to study the temperature, so that better understanding could be developed for the meteorological sub-divisions over India. [ABSTRACT FROM AUTHOR]

China, India, and the USA are the countries with the highest energy consumption and CO2 emissions globally. As per the report of datacommons.org, CO2 emission in India is 1.80 metric tons per capita, which is harmful to living beings, so this paper presents India's detrimental CO2 emission effect with the prediction of CO2 emission for the next 10 years based on univariate time-series data from 1980 to 2019. We have used three statistical models; autoregressive-integrated moving average (ARIMA) model, seasonal autoregressive-integrated moving average with exogenous factors (SARIMAX) model, and the Holt-Winters model, two machine learning models, i.e., linear regression and random forest model and a deep learning-based long short-term memory (LSTM) model. This paper brings together a variety of models and allows us to work on data prediction. The performance analysis shows that LSTM, SARIMAX, and Holt-Winters are the three most accurate models among the six models based on nine performance metrics. Results conclude that LSTM is the best model for CO2 emission prediction with the 3.101% MAPE value, 60.635 RMSE value, 28.898 MedAE value, and along with other performance metrics. A comparative study also concludes the same. Therefore, the deep learning-based LSTM model is suggested as one of the most appropriate models for CO2 emission prediction. [ABSTRACT FROM AUTHOR]

Monitoring of river water is necessary to reveal its quality and pollution level so that we can protect human health and the environment. The present study explored the water quality of the Narmada River in India. To evaluate the water quality of the Narmada River, water samples were collected from 13 sites during the pre- and post-monsoon seasons, and were analyzed for different physicochemical parameters. The results from the analysis were used for the development of the entropy-river water quality index (ERWQI). The ERWQI was used to estimate the Narmada river water quality for two different uses: drinking after disinfection (ERWQId) and bathing (ERWQIb). The machine-learning-based classification models, namely the Logistic regression (LR), Support Vector (SV), K-Nearest Neighbor (KNN), Random Forest (RF), and Gradient Boosting (GB) models were examined to predict and classify ERWQI. The precision, recall, F1 score, and confusion matrix were used to evaluate the performance of the model. The findings of this study identified the LR model as the most accurate classification model with the highest accuracy score for both the ERWQId and ERWQIb. Moreover, this study also revealed that the water quality of the Narmada River was unsuitable for drinking after disinfection and hence, before any further use it requires treatment through conventional or an advanced techniques. However, the ERWQIb of the Narmada River was categorized as excellent to fair. This study has broad implications for the classification of river water quality and can provide some very useful information to monitoring agencies and policymakers. [ABSTRACT FROM AUTHOR]

Integrated large-scale solid waste management (SWM) policies are the need of the hour to design, develop and sustain SWM models. An accurate prediction and forecasting of municipal solid waste generation (MSWG) rate are essential for such advanced strategies. The primary objective of this study is to examine the criticality of demographic and socio-economic parameters for the fair prediction and forecasting of the MSWG rate. Machine learning (ML) models were formulated by mapping solid waste quantities at the municipal level with socio-economic and demographic variables of Guwahati city. Tree-based ML algorithms, namely decision tree (DT), random forest (RF) and gradient boosting (GB), were applied to build the models with 1936 data size. The moving average (MA) approaches were adapted for the forecasting of the MSWG rate. Model validation resulted in a root mean square error, RMSE (3.01), mean absolute error, MAE (2.86) and coefficient of determination, R2 (0.99) for the GB model and correlation coefficient (r) of 0.82 between observed and predicted values and thereby resulted in best performance in conjunction with DT and RF. With the exponential MA, the forecasted RMSE and R2 for GB, RF and DT were 2.12, 3.63 and 4.22; and 0.981, 0.972 and 0.967, respectively. However, with a model accuracy of 97%, the computation time for GB model (19.18 min) exhibited maximum due to its high complexity. The overall methodology involved developing effective tools to aid in regional SWM and planning through the integration of data sources in the public domain, pre-processing and modelling from diverse sources. [ABSTRACT FROM AUTHOR]

In the present study, a model has been developed for nowcasting using the Automatic Weather Station (AWS) data collected from Thiruvananthapuram, Kerala, India. The Proposed model is based on machine learning techniques: Random Forest (RF), which had been coupled with Principal Component Analysis (PCA). PCA minimizes the presence of multicollinearity issue in the AWS data, which enables the RF to access independent effects of predictors efficiently to predict rainy or non-rainy conditions of the atmosphere for the next 4 hours during the peak summer monsoon of month July. The sensitivity and feasibility of the model were tested for different predictors such as wind speed, temperature, pressure, relative humidity, sunshine, and rainfall, where the demarcation between rainy and non-rainy events was computed using a precision-recall curve. The performance of proposed algorithms for rainfall events is evaluated by using different statistics such as accuracy, precision, recall, probability of detection (POD), and false alarm rate (FAR). The proposed algorithm is found to nowcast with an accuracy rate of 90% and the probability of detection is 68%. The analysis of in-situ observations establishes that the most influential predictors for the nowcasting of rainfall are atmospheric pressure and wind speed. [ABSTRACT FROM AUTHOR]

The growing concerns surrounding water supply, driven by factors such as population growth and industrialization, have highlighted the need for accurate estimation of streamflow at the river basin level. To achieve this, rainfall-runoff models are widely employed as valuable tools in watershed management. For this specific study, two modelling approaches were employed: the Soil and Water Assessment Tool (SWAT) model and a set of eight artificial intelligence (AI) models. The AI models consisted of seven data-driven approaches, namely k-nearest neighbour regression, support vector regression, linear regression, artificial neural networks, random forest regression, XGBoost, and Histogram-based Gradient Boost regression. Additionally, a deep learning model known as Long Short-Term Memory (LSTM) was also utilized. The study focused on monthly streamflow modelling in the Murredu River basin, with a calibration period from 1999 to 2003 and a validation period from 2004 to 2005, spanning a total of 7 years from 1999 to 2005. The results indicated that all nine models were generally suitable for simulating the rainfall-runoff process, with the LSTM model demonstrating exceptional performance in both the calibration (R2 is 0.97 and NSE is 0.96) and validation (R2 is 0.97 and NSE is 0.92) periods. Its high coefficient of determination (R2) and Nash–Sutcliffe efficiency (NSE) values indicated its superior ability to accurately model the rainfall-runoff relationship. While the other models also produced satisfactory results, the findings suggest that selecting the most efficient model, such as the LSTM model, could significantly contribute to the effective management and planning of sustainable water resources in the Murredu watershed. [ABSTRACT FROM AUTHOR]

Climate change significantly impacts the global hydrological cycle, leading to pronounced shifts in hydroclimatic extremes such as increased duration, occurrence, and intensity. Despite these significant changes, our understanding of hydroclimatic risks and hydrological resilience remains limited, particularly at the catchment scale in peninsular India. This study aims to address this gap by examining hydroclimatic extremes and resilience in 54 peninsular catchments from 1988 to 2011. We initially assess extreme precipitation and discharge indices and estimate design return levels using non-stationary Generalized Extreme Value (GEV) models that use global climate modes (ENSO, IOD, and AMO) as covariates. Further, hydrological resilience is evaluated using a convex model that inputs simulated discharge from the best hydrological model among SVM, RVM, random forest, and a conceptual model (abcd). Our analysis shows that the spatial patterns of mean extreme precipitation indices (R1 and R5) mostly resemble with extreme discharge indices (Q1 and Q5). Additionally, all extreme indices, including R1, Q1, R5, and Q5, demonstrate non-stationary behavior, indicating the substantial influence of global climate modes on extreme precipitation and flooding across the catchments. Our results indicate that the random forest model outperforms the others. Furthermore, we find that 68.52% of the catchments exhibit low to moderate hydrological resilience. Our findings emphasize the importance of understanding hydroclimatic risks and catchment resilience for accurate climate change impact predictions and effective adaptation strategies. [ABSTRACT FROM AUTHOR]

The understating of natural resources and hazards is very fundamental from spatial perspective to reduce loss of resource and human lives. For this, the main aim of the current research is to synthesize the three natural resources (groundwater, wetland, and forest) into one multi-resource (MR) potentiality map and three natural hazards (flood, landslide, and shoreline erosion) into one multi-hazard (MH) susceptibility map. To achieve this goal, several inventories, geo-environmental factors, satellite bands, and indices have been taken as input data sets. Random forest (RF) model has been considered for individual mapping (except shoreline erosion mapping) due to its high precision. For shoreline erosion mapping, digital shoreline analysis system (DSAS) model has been employed. The accuracies of the model have been determined from the area under receiver operating characteristic (AUROC) curve, producer accuracy (PA), and user accuracy (UA). RF model has more than 90% prediction accuracy in different resource and hazard mapping, whereas for the forest mapping, PA and UA are 90% and 80%, respectively. The results of this study for multi-resource mapping show forest (24.05%) and groundwater (22.28%) as the major resources, whereas flood (17.27%) is the most destructive in comparison with other hazards. The multi-resource and multi-hazard maps of the research area provide an important tool to land managers and policymakers for sustainable development and management. [ABSTRACT FROM AUTHOR]

Agriculture, meteorological, and hydrological drought is a natural hazard which affects ecosystems in the central India of Maharashtra state. Due to limited historical data for drought monitoring and forecasting available in the central India of Maharashtra state, implementing machine learning (ML) algorithms could allow for the prediction of future drought events. In this paper, we have focused on the prediction accuracy of meteorological drought in the semi-arid region based on the standardized precipitation index (SPI) using the random forest (RF), random tree (RT), and Gaussian process regression (GPR-PUK kernel) models. A different combination of machine learning models and variables has been performed for the forecasting of metrological drought based on the SPI-6 and 12 months. Models were developed using monthly rainfall data for the period of 2000–2019 at two meteorological stations, namely, Karanjali and Gangawdi, each representing a geographical region of Upper Godavari river basin area in the central India of Maharashtra state which frequently experiences droughts. Historical data from the SPI from 2000 to 2013 was processed to train the model into machine learning model, and the rest of the 2014 to 2019-year data were used for testing to forecast the SPI and metrological drought. The mean square error (MSE), root mean square error (RMSE), adjusted R2, Mallows' (Cp), Akaike's (AIC), Schwarz's (SBC), and Amemiya's PC were used to identify the best combination input model and best subregression analysis for both stations of SPI-6 and 12. The correlation coefficient (r ), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE) were used to perform evaluation for SPI-6 and 12 months of both stations with RF, RT, and GPR-PUK kernel models during the training and testing scenarios. The results during testing phase revealed that the RF was found as the best model in forecasting droughts with values of r , MAE, RMSE, RAE (%), and RRSE (%) being 0.856, 0.551, 0.718, 74.778, and 54.019, respectively, for SPI-6 while 0.961, 0.361, 0.538, 34.926, and 28.262, respectively, for SPI-12 scales at Gangawdi station. Further, the respective values of evaluators at Karanjali station were 0.913 and 0.966, 0.541 and 0.386, 0.604 and 0.589, 52.592 and 36.959, and 42.315 and 31.394 for PUK kernel and RT models, respectively, during SPI-6 and SPI-12. Machine learning models are potential drought warning techniques because they take less time, have fewer inputs, and are less sophisticated than dynamic or scientific models. [ABSTRACT FROM AUTHOR]

The predictive models from different machine learning methods are useful tools for sensitive geo-mechanical properties determination. Many such models were previously established to manage time efficiency in a real-field scenario. The objective of this study is to assess and optimize three machine learning-based approaches, namely Support Vector Machine (SVM), Random Forest (RF) and Deep Neural Network (DNN), for predicting the performance of lateritic soil shear strength. The laboratory tests were accomplished to obtain the index parameters after collecting the representative lateritic soil samples along the Ratnagiri-Sangameshwar section of National Highway 66 in Maharashtra, India. To produce the training and test datasets for the prediction models, the intrinsic properties of the soil are documented, including unit weight, maximum dry density, liquid limit, plasticity index and optimal moisture content. Further, 102 lab-tested lateritic soil data of input parameters are implemented to perform the three supervised learning algorithms. The performance and accuracy of the studied methods were measured using the root mean square error (RMSE) and goodness of fit (R2). The outcome demonstrates that the deep neural network model has the highest prediction accuracy for the residual soil shear strength among the three distinct proposed machine learning (ML) models. [ABSTRACT FROM AUTHOR]

This study aims to estimate and analyse extreme climate indices such as standardised precipitation index (SPI) coupled with enviro-met (air pollutants and meteorological) parameters over the Vidarbha region from 1980 to 2019. Seasonal SPI, also known as the draught index, is derived from rainfall data using the R language. An attempt is made to determine the best combination of enviro-met on SPI using the random forest (RF) models. The study region is divided into four zones to assess the microclimatic impact on the forecast model. Three sets of data combinations, viz., meteorological and air pollution parameters, are applied for SPI prediction using RF. The autoregressive integrated moving average (ARIMA) model is also used for a future scenario projection. It is observed from the projection results that the drought severity is enhancing with time. The drought severity scale from 1980 to 1989 is found to be between − 1 and 1, but the scale increases from 1990 to 2019 (− 3). From 1990 to 2019, SPI's negative (−) scale has become more prominent in all Vidarbha regions. These trends are indicative of drought severity and will have a significant impact on both life and property. [ABSTRACT FROM AUTHOR]

Air pollution has become one of the environmental concerns in recent years due to its harmful threats to human health. To inform people about the air quality in their living areas, it is essential to measure the extent of pollution in the atmosphere. Air pollution sensors are assembled at static, fixed-site measurement monitoring stations to acquire data. The data can be processed at the fixed stations or transmitted to the server to predict the Air Quality Index (AQI). Some previous studies applied machine learning algorithms to predict the AQI. Even though those works showed good performance on specific data, the results are not consistent on different datasets. Moreover, to serve the need for low-cost AQI tracking and prediction, lightweight machine learning algorithms can be directly integrated into microcontroller hardware systems. This study proposed a new method that combines (i) air pollution data processing techniques and (ii) lightweight machine learning algorithms to enhance the AQI predicting performance. Three algorithms, namely Decision Tree, Random Forest, and XGBoost, were compared via three evaluation metrics: MAE, RMSE, and R2 to propose the best model in AQI prediction. Two different public datasets, which were both collected in different regions in India were used to verify our proposed method. XGBoost outperformed in predicting the AQI values. Thus, XGBoost is selected for the low-cost AQI prediction device assembled at fixed-site measurement stations. [ABSTRACT FROM AUTHOR]

Elevated fluoride in groundwater is a severe problem in India due to its extensive occurrence and detrimental health impacts on the large population that thrives on groundwater. Although fluoride is primarily a geogenic pollutant, existing model-based studies lack the amalgamation of the influence of geologic factors, specifically tectonics, for identifying groundwater fluoride distribution. This drawback encourages the present study to investigate the association of the tectonic framework with fluoride in a multi-model approach. We have applied three machine learning models (random forest, boosted regression tree, and logistic regression) to predict elevated groundwater fluoride based on fluoride measurements across India. The random forest model outperformed other models with an accuracy of 93%. Tectonics was found to be one of the most important predictors alongside "depth to water table." Two major areas of high risk identified were the northwest parts and the south–southeast cratonic peninsular region. The random forest model also performed significantly well over the validation dataset. We estimate that nearly 257 million people are exposed to elevated fluoride risk in India. We endeavor that the findings of our study would be an effective tool for identifying the areas at risk of elevated fluoride and also assist in undertaking effective groundwater management strategies. [ABSTRACT FROM AUTHOR]

Climate change poses a major threat to global food security. Agricultural systems that rely on monsoon rainfall are especially vulnerable to changes in climate variability. This paper uses machine learning to deepen understanding of how monsoon variability impacts agricultural productivity. We demonstrate that random forest modelling is effective in representing rice production variability in response to monsoon weather variability. Our random forest modelling found monsoon weather predictors explain similar levels of detrended anomaly variation in both rice yield (33%) and area harvested (35%). The role of weather in explaining harvested rice area highlights that production area changes are an important pathway through which weather extremes impact agricultural productivity, which may exacerbate losses that occur through changes in per-area yields. We find that downwelling shortwave radiation flux is the most important weather variable in explaining variation in yield anomalies, with proportion of area under irrigation being the most important predictor overall. Machine learning modelling is capable of representing crop-climate variability in monsoonal agriculture and reveals additional information compared to traditional parametric models. For example, non-linear yield and area responses of irrigation, monsoon onset and season length all match biophysical expectations. Overall, we find that random forest modelling can reveal complex non-linearities and interactions between climate and rice production variability. [ABSTRACT FROM AUTHOR]

Assessment of spatiotemporal dynamics of meteorological variables and their forecast is essential in the context of climate change. Such analysis can help suggest possible solutions for flora and fauna in protected areas and adaptation strategies to make forests and communities more resilient. The present study attempts to analyze climate variability, trend and forecast of temperature and rainfall in the Valmiki Tiger Reserve, India. We utilized rainfall and temperature gridded data obtained from the Indian Meteorological Department during 1981–2020. The Mann–Kendall test and Sen's slope estimator were employed to examine the time series trend and magnitude of change at the annual, monthly and seasonal levels. Random forest machine learning algorithm was used to estimate seasonal prediction and forecasting of rainfall and temperature trend for the next ten years (2021–2030). The predictive capacity of the model was evaluated by statistical performance assessors of coefficient of correlation, mean absolute error, mean absolute percentage error and root mean squared error. The findings revealed a significant decreasing trend in rainfall and an increasing trend in temperature. However, a declining trend for maximum temperature has been observed for winter and post-monsoon seasons. The results of seasonal forecasting exhibited a considerable decrease in rainfall and temperature across the Reserve during all the seasons. However, the temperature will increase during the summer season. The random forest machine learning algorithm has shown its effectiveness in forecasting the temperature and rainfall variables. The findings suggest that these approaches may be used at various spatial scales in different geographical locations. [ABSTRACT FROM AUTHOR]

Pigeon pea is the second most important grain legume in India, primarily grown under rainfed conditions. Any changes in agro-climatic conditions will have a profound influence on the productivity of pigeon pea (Cajanus cajan) yield and, as a result, the total pulse production of the country. In this context, weather-based crop yield prediction will enable farmers, decision-makers, and administrators in dealing with hardships. The current study examines the application of the stepwise linear regression method, supervised machine learning algorithms (support vector machines (SVM) and random forest (RF)), shrinkage regression approaches (least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)), and artificial neural network (ANN) model for pigeon pea yield prediction using long-term weather data. Among the approaches, ANN resulted in a higher coefficient of determination (R2 = 0.88–0.99), model efficiency (0.88–1.00) with subsequent lower normalised root mean square error (nRMSE) during calibration (1.13–12.55%), and validation (0.33–21.20%) over others. The temperature alone or its interaction with other weather parameters was identified as the most influencing variables in the study area. The Pearson correlation coefficients were also determined for the observed and predicted yield. Those values also showed ANN as the best model with correlation values ranging from 0.939 to 0.999 followed by RF (0.955–0.982) and LASSO (0.880–0.982). However, all the approaches adopted in the study were outperformed the statistical method, i.e. stepwise linear regression with lower error values and higher model efficiency. Thus, these approaches can be effectively used for precise yield prediction of pigeon pea over different districts of Karnataka in India. [ABSTRACT FROM AUTHOR]

The study on land use and land cover (LULC) changes assists in analyzing the change and regulates environment sustainability. Hence, this research analyzes the Northern TN coast, which is under both natural and anthropogenic stress. The analysis of LULC changes and LULC projections for the region between 2009–2019 and 2019–2030 was performed utilizing Google Earth Engine (GEE), TerrSet, and Geographical Information System (GIS) tools. LULC image is generated from Landsat images and classified in GEE using Random Forest (RF). LULC maps were then framed with the CA-Markov model to forecast future LULC change. It was carried out in four steps: (1) change analysis, (2) transition potential, (3) change prediction, and (4) model validation. For analyzing change statistics, the study region is divided into zone 1 and zone 2. In both zones, the water body shows a decreasing trend, and built-up areas are in increasing trend. Barren land and vegetation classes are found to be under stress, developing into built-up. The overall accuracy was above 89%, and the kappa coefficient was above 87% for all 3 years. This study can provide suggestions and a basis for urban development planning as it is highly susceptible to coastal flooding. [ABSTRACT FROM AUTHOR]

The tea agroforestry system has great economic potential by supporting livelihood and food security while advancing ecological services by sequestering a large amount of carbon. Despite a large area under tea cultivation in India, little has been studied on the spatial distribution of aboveground biomass (AGB) of the tea agroforestry systems. Hence, the present study aims to map the spatial distribution of AGB of tea agroforestry systems in Barak valley, Assam, northeast India, by integrating Sentinel-2 satellite imagery and field inventory data using a random forest (RF) algorithm. The study reveals 330.69 km2 area under tea cultivation in Barak valley which is 4.78% of the total geographical area of the region. The predicted AGB of tea agroforestry systems ranged from 30 to 124 Mg ha−1 with a mean AGB of 75 Mg ha−1. It was observed that RF could effectively predict the AGB (R2 = 0.86, RMSE = 7.50 Mg ha−1, and %RMSE = 9.94%) with a set of five optimized spectral variables, viz., Normalized Difference Vegetation Index, Green Normalized Difference Vegetation Index, Normalized Difference Infrared Index, Normalized Difference Water Index and Atmospherically Resistant Vegetation Index derived from Sentinel-2 satellite data. The study provided a cost-effective approach, with freely available satellite data, algorithm, and software for effectively mapping the spatial distribution of AGB of tea agroforestry system. The approach adopted in the present study can be followed to map and monitor the carbon stock of agroforestry systems for better management. [ABSTRACT FROM AUTHOR]

In the last decade, air pollution has become one of the vital environmental issues and has expanded its wings day by day. Prediction of air quality plays a crucial role in warning people about the air quality levels. With the help of this, we can make the proper mechanism for reducing the overall impact of bad air quality on individuals' health. In this paper, we are focused on developing a mechanistic and quantitative prediction model for the prediction of the Air Quality Index (AQI) and Air Pollutant Concentration (NOx) levels with a clear environmental interpretation. The proposed model is based on the Linear Regression based Recursive Feature Elimination with Random Forest Regression (RFERF). For the experimental analysis, the seven well-established machine learning models have been taken, and these models are compared with our proposed model to find out their suitability and correctness. The Mean Absolute Percentage Error (MAPE), mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and Coefficient of Determination (R2 score) have been used to validate the performance of prediction models. For the prediction of AQI and NOx, the data of the Central Pollution Control Board of India has been taken. The proposed model performs superior as compared to other prediction models with better accuracy and a higher prediction rate. This work also explains that linking machine learning with sensor-generated AQI data for air quality prediction is an adequate and appropriate way to solve some related environment glitches. Apart from this, the impact of air pollution on individuals' health due to high levels of AQI, NOx, and other pollutants with the possible solutions has also been covered. [ABSTRACT FROM AUTHOR]

This research aims to generate a landslide susceptibility map (LSM) for the Bhagirathi river basin located in the Tehri Garhwal district of Uttarakhand state in India. For this study, we incorporated and utilized machine learning novel ensemble models, namely: Generalize Linear Model (GLM), Random Forest (RF), Convolutional Neural Network (CNN), GLM-RF, CNN-RF, CNN-GLM and CNN-GLM-RF. The above-specified ensemble models were incorporated for the preparation of LSM. A total of 171 landslide locations were chosen and studied for the preparation of landslide inventory. From the landslide inventory, 70% of landslides were utilized for the training purpose, whereas the rest, 30%, were used for the validation purpose. In the ongoing research study, a total of 17 landslide conditioning factors (LCFs) were utilized, and the analysis for multi-collinearity was performed by tolerance (TOL) as well as variance inflation factor (VIF) methods. These LSM were then validated through receiver operating characteristic curve (ROC), mean absolute error (MAE), root mean square error (RMSE) and Chi-Square methods. Finally, the outcomes of the analysis, as well as validation models, show that the CNN model proves to be the most effective for predicting landslide susceptibility in the study area. The study found that the methods incorporated for the area under consideration can be applied to the regions having similar geo-environmental factors globally. [ABSTRACT FROM AUTHOR]

With the present trend toward digitization in many areas of urban planning and development, accurate object classification is becoming increasingly vital. To develop machine learning models that can effectively classify the broader region, it is crucial to have accurately labelled datasets for object extraction. However, the process of generating sufficient labelled data for machine learning models remains challenging. A recently developed AI-assisted segmentation approach called the Segment Anything Model (SAM) offers a solution to enhance the labelling of complex and intricate image structures. By utilizing SAM, the accuracy and consistency of annotation results can be improved, while also significantly reducing the time required for annotation. This paper aims to assess the efficiency of SAM annotated labels for training machine learning models using high-resolution remote sensing data captured by UAVs (Unmanned Aerial Vehicles) in the peri-urban region of Anad, Kerala, India. A comparative analysis was conducted to evaluate the performance of training datasets generated using SAM and manual labelling with existing tools. Multiple machine learning models, including Random Forest, Support Vector Machine, and XGBoost, were employed for this analysis. The findings demonstrate that employing the XGBoost algorithm in combination with SAM annotated labels yielded an accuracy of 78%. In contrast, the same algorithm trained with the manually labeled dataset achieved an accuracy of only 68%. A similar pattern was observed when employing the Random Forest algorithm, with accuracies of 78% and 60% while using SAM annotated labels and manual labels, respectively. These outcomes unequivocally showcase the enhanced effectiveness and dependability of the SAM-based segmentation method in producing accurate results. [ABSTRACT FROM AUTHOR]

This study examined landslide susceptibility, an increasingly common problem in mountainous regions across the world as a result of urbanization, deforestation, and various natural processes. The Rangit River watershed in Sikkim Himalaya is one of the most landslide-prone areas in India. The main objective of this study was to produce landslide susceptibility maps of the Rangit River watershed using novel ensembles of random forest tree (RFT) with support vector machine (RFT-SVM), artificial neural network (RFT-ANN), naïve Bayes tree (RFT-NBT), and logistic model tree (RFT-LMT). An inventory of landslides was created using historical landslide data, government and scientific studies, and Google Earth's high-resolution satellite images. The landslide/non-landslide locations were split 70/30 for training and validating the models, respectively. Eleven landslide conditioning factors were selected based on their predictive ability, determined using the information gain method, and each factor's importance was derived. A landslide susceptibility index was then estimated by weighted overlay using a model builder in a GIS (Geographic Information System) environment. Based on the area under the curve and statistical metrics, RFT-LMT was identified as the best model. The results showed that approximately 40% of the Rangit River watershed has high to very high susceptibility to landslides. This study's findings will be useful for policy-makers and land use planners in managing and mitigating future landslides in the study area. [ABSTRACT FROM AUTHOR]

Coronavirus has been identified as one of the deadliest diseases and the WHO has declared it a pandemic and a global health crisis. It has become a massive challenge for humanity. India is also facing its fierceness as it is highly infectious and mutating at a rapid rate. To control its spread, many interventions have been applied in India since the first reported case on January 30, 2020. Several studies have been conducted to assess the impact of climatic and weather conditions on its spread in the last one and half years span. As it is a well-established fact that temperature and humidity could trigger the onset of diseases such as influenza and respiratory disorders, the relationship of meteorological variables with the number of COVID-19 confirmed cases has been anticipated. The association of several meteorological variables has therefore been studied in the past with the number of COVID-19 confirmed cases. The conclusions in those studies are based on the data obtained at an early stage, and the inferences drawn based on those short time series studies may not be valid over a longer period. This study attempted to assess the influence of temperature, humidity, wind speed, dew point, previous day's number of deaths, and government interventions on the number of COVID-19 confirmed cases in 18 districts of India. It is also attempted to identify the important predictors of the number of confirmed COVID-19 cases in those districts. The random forest model and the hybrid model obtained by modelling the random forest model's residuals are used to predict the response variable. It is observed that meteorological variables are useful only to some extent when used with the data on the number of the previous day's deaths and lockdown information in predicting the number of COVID-19 cases. Partial lockdown is more important than complete or no lockdown in predicting the number of confirmed COVID-19 cases. Since the time span of the data in the study is reasonably large, the information is useful to policymakers in balancing the restriction activities and economic losses to individuals and the government. [ABSTRACT FROM AUTHOR]

Floods have a significant economic, social, and environmental impact in developing countries like India. Settlements in flood hazard zones increase flood risk due to a lack of information and awareness. The present study proposed a machine learning-based framework to identify such flood risk zones for the lower Narmada basin in India. Flood hazard factors like elevation and slope of the terrain, distance from main river network, drainage density, annual average rainfall of the area, and land-use land-cover (LULC) characteristics, as well as flood vulnerability factors like population density, agricultural production, and road–river intersections, were used as predictors in the random forest algorithm to predict the flood depth in the region. Initially, the flood depth obtained from the hydrodynamic model was used as a predict and to train the model and determine the weightage of each predictor. The RandomizedSeachCV technique was used to optimize hyperparameters of the random forest algorithm. The obtained results from variable importance of random forest show that the elevation of the terrain, LULC characteristics, distance from the main river network, and rainfall are the major contributors to cause flood risk in the area. Furthermore, the possibility of using the IoT-based sensor to develop the real-time flood risk mapping framework is described. The developed flood risk map can assist policymakers, stakeholders, and citizens in developing guidelines, taking preventive measures, and avoid unnecessary settlements in flood risk zones. [ABSTRACT FROM AUTHOR]

Background: Large-scale hunting and various anthropogenic pressures in the recent past have pushed the Asiatic caracal (Caracal caracal schmitzi), an elusive medium-sized and locally threatened felid species towards local extinction in India. Though widely distributed historically, it has been sparsely reported from several regions of central and northern states in India till twentieth century. Later, the species distribution became confined only to the states of Rajasthan, Gujarat and Madhya Pradesh, which have had reported sightings in the twenty-first century. In order to highlight the potentially suitable habitats for Asiatic caracals in India, we targeted forth-filtering of the spatial model ensemble by creating and utilizing the validated and spatially thinned species presence information (n = 69) and related ecological variables (aridity, NDVI, precipitation seasonality, temperature seasonality, terrain ruggedness), filtered with anthropological variable (nightlight). Results: Out of eight spatial prediction models, the two most parsimonious models, Random Forest (AUC 0.91) and MaxEnt (AUC 0.89) were weighted and ensembled. The ensemble model indicated several clustered habitats, covering 1207.83 km2 areas in Kachchh (Gujarat), Aravalli mountains (Rajasthan), Malwa plateau (Rajasthan and Madhya Pradesh), and Bundelkhand region (Madhya Pradesh) as potentially suitable habitats for caracals. Output probabilities of pixels were further regressed with converted vegetation height data within selected highly potential habitats, i.e., Ranthambore Kuno Landscape (RKL) (suitability ~ 0.44 + 0.03(vegetation height) **, R2 = 0.27). The regression model inferred a significant positive relation between vegetation height and habitat suitability, hence the lowest ordinal class out of three classes of converted vegetation height was masked out from the RKL, which yielded in an area of 567 km2 as potentially highly suitable habitats for caracals, which can be further proposed as survey areas and conservation priority areas for caracals. Conclusion: The study charts out the small pockets of landscape in and around dryland protected areas, suitable for caracal in the Indian context, which need attention for landscape conservation. [ABSTRACT FROM AUTHOR]

In 2016, India's Insolvency and Bankruptcy Board laid out the Insolvency and Bankruptcy Code for Indian companies struggling financially and seeking solvency or resolution. Since then, around three hundred firms have filed for bankruptcy resolution in India as per IBC 2016. This research studies the financial distress in Indian companies listed on the Bombay Stock Exchange (BSE) by taking a balanced sample of companies. The extant research has employed various methodologies. We apply state-of-the-art machine learning techniques for the task of prediction, such as logistic regression, lasso regression, decision tree, bagging, boosting, and support vector machine. We selected eighteen firm-level variables as explanatory variables, among which the ratio of Market capitalization/Debt came out to be the most critical variable in all the models. This variable is suggested as a measure of leverage in Altman's z-score model. The finding on the significance of the ratio of Market capitalization/Debt is in line with the existing literature. Debt is expected to be higher for financially distressed firms than the financially healthy ones. Further, as the investors might not be interested in investing in a distressed firm, it is likely to lead to a further decrease in market capitalization in financially distressed firms. The random forest bagging model achieved the highest accuracy, recall, and area under the curve (AUC) for the receiver operating characteristic (ROC) curve on the performance of the models. The boosting model achieved the highest precision. [ABSTRACT FROM AUTHOR]

The urbanisation process moves quickly in emerging nations like India and Bangladesh, transforming natural landscapes into unsustainable landscapes. Consequently, growing development has had a significant impact on agricultural land as a natural environment. Moreover, there is a scarcity of research on fragmentation probability modelling in the extant literature. Thus, by combining random forest (RF) and bagging with the datasets which are multi-temporal in a GIS framework, the probability of fragmentation of LULC at Jangipur subdivision in India and Bangladesh can be modelled. Parallelepiped, Mohalnobis distance, support vector machines (SVM), spectral angle mapper (SAM), and artificial neural networks (ANN) classifiers were used for LULC classification, where SVM (Kappa coefficient: 0.87) surpassed other classifiers. The LULC maps for 1990, 2000, 2010, and 2020 were created using the best classifier (SVM). During this time, the built-up area grew from 23.769 to 158.125 km2. Then, using an ANN-based cellular automata model, the future LULC map for 2030 was predicted (CA-ANN). In 2030, the built-up area would be 201.58 km2. Then the matrices of class and landscape were taken out of the LULC maps utilising FRAGSTAT software and included the patch number (NP), largest patch index (LPI), edge density (ED), contagion index (percentage) (CONTAG), perimeter and area (P/A), aggregation index (AI), landscape percentage (PLAND), the area of class (CA), patch density (PD), edge in total (TE), total core area (TCA), and largest shape index (LSI). The validation results revealed that bagging (0.915 = AUC) and RF (0.874 = AUC) are capable of assessing fragmentation probability, with the bagging model having the greatest precision level of the two. Almost 20% of the total LULC was in a high and very high zone of fragmentation vulnerability, necessitating the use of direct measures to safeguard it. As a result, adequate LULC management is required. [ABSTRACT FROM AUTHOR]

Over the years, many organizations across the globe have conducted various studies pertaining to air pollution and its ill effects. The results of these studies substantially conclude that a plethora of people succumbs to the adversities caused by the ever-increasing air pollutants. In this investigation, M5P, random forest (RF)- and Gaussian process (GP)-based approaches are used to predict the tropospheric ozone for Amritsar, Punjab state of India, metropolitan area. The models proposed were based on ten input parameters viz. particulate matter PM2.5, particulate matter PM10, sulphur dioxide (SO2), nitrogen dioxide (NO2), nitric oxide (NO), ammonia (NH3), temperature (T), solar radiation (SR), wind direction (WD) and wind speed (WS), while the tropospheric ozone (O3) was an output parameter. Three most popular statistical parameters such as correlation coefficient (CC), mean absolute error (MAE) and root mean square error (RMSE) were used for the assessment of the developed models. In comparison, it was found that better results were achieved with random forest-based model with CC value as 0.8850, MAE value as 0.0593 and RMSE value as 0.0772 for testing stage. The suggested models are expected to save cost of instrument, cost of labour work, time and contribute to greater accuracy. A result of sensitivity investigation concludes that the solar radiation is the most influencing parameter in estimating the actual values of O3 based on the current data set. [ABSTRACT FROM AUTHOR]

This paper compares four prediction methods, namely random forest regressor (RFR), SARIMAX, Holt-Winters (H-W), and the support vector regression (SVR), to forecast the total CO2 emission from the paddy crop in India. The major objective of this study is to compare these four models and suggest an effective model for the prediction of total CO2 emission. Data from 1961 to 2018 has been categorised into two parts: training and test data. The study forecasts total CO2 emission from paddy crops in India from 2019 to 2025. A comparison of mean absolute percentage error (MAPE) and the mean square error (MSE) highlights the differences in accuracy among the four models. The mean absolute percentage eror (MAPE) and the mean square error (MSE) for the four methods are RFR (MAPE: 5.67; MSE: 549,900.02), SARIMAX (MAPE: 1.67; MSE:70,422.35), H-W (MAPE:0.75; MSE:16,648.58), and SVR (MAPE: 0.91; MSE: 17,832.4). The values of MAPE and MSE with the Holt-Winters (H-W) and the support vector regression (SVR) are relatively low as compared to SARIMAX and RFR. Based on these results, it can be inferred that H-W and SVR were found suitable models to forecast the total CO2 emission from paddy crops. Holt-Winters model predicted 14,364.97 for the year 2025, and SVR predicted 13,696.67 for the year 2025. The decision-maker can use these predictions to build a suitable policy for the future. This approach can be contrasted with other forecasting methods, such as the neural network, and train the model to achieve better forecast accuracy. [ABSTRACT FROM AUTHOR]

Precise and reliable runoff forecasting is crucial for water resources planning and management. The present study was conducted to test the applicability of different data-driven techniques including artificial neural networks (ANN), support vector machine (SVM), random forest (RF) and M5P models for runoff forecasting for the lead time of 1 day and 2 days in the Koyna River basin, India. The best input variables for the development of the models were selected by applying the Gamma test (GT). Two different scenarios were considered to select the input variables for 2 days ahead runoff forecasting. In the first scenario, the output of 1 day ahead runoff (t + 1) was not used as an input while it was also used as an input along with other input variables for the development of the models in the second scenario. For 2 days ahead runoff forecasting, the models developed by adopting the second scenario performed more accurately than that of the first scenario. The RF model performed the best for 1 day ahead runoff forecasting with root mean square error (RMSE), coefficient of efficiency (CE), correlation coefficient (r) and coefficient of determination (R2) values of 168.94 m3/s, 0.67, 0.84 and 0.704, respectively, during the test period. For 2 days ahead runoff forecasting, RF and ANN models performed the best in the first and second scenario, respectively. In 2 days ahead runoff forecasting, RMSE, CE, r and R2 values were observed to be 169.72 m3/s, 0.67, 0.84, 0.7023 and 148.55 m3/s, 0.74, 0.87, 0.76 in the first and second scenarios, respectively, during the test period. Finally, the results revealed that the addition of 1 day ahead runoff forecast increased the forecast accuracy of 2 days ahead runoff forecasts. In addition, the dependability of the various models was determined using the uncertainty analysis. [ABSTRACT FROM AUTHOR]

Multi-Model Ensembles (MMEs) are used for improving the performance of GCM simulations. This study evaluates the performance of MMEs of precipitation, maximum temperature and minimum temperature over a tropical river basin in India developed by various techniques like arithmetic mean, Multiple Linear Regression (MLR), Support Vector Machine (SVM), Extra Tree Regressor (ETR), Random Forest (RF) and long short-term memory (LSTM). The 21 General Circulation Models (GCMs) from National Aeronautics Space Administration (NASA) Earth Exchange Global Daily Downscaled Projections (NEX-GDDP) dataset and 13 GCMs of Coupled Model Inter-comparison Project, Phase 6 (CMIP6) are used for this purpose. The results of the study reveal that the application of a LSTM model for ensembling performs significantly better than models in the case of precipitation with a coefficient of determination (R2) value of 0.9. In case of temperature, all the machine learning (ML) methods showed equally good performance, with RF and LSTM performing consistently well in all the cases of temperature with R2 value ranging from 0.82 to 0.93. Hence, based on this study RF and LSTM methods are recommended for creation of MMEs in the basin. In general, all ML approaches performed better than mean ensemble approach. [ABSTRACT FROM AUTHOR]

Tropical cyclones as natural disturbances, influence ecosystem structure, function and dynamics at the global scale. This study assesses the inundation due to the super cyclone Amphan in coastal districts of eastern India by leveraging the computational power of Google Earth Engine (GEE) and the availability of high resolution Sentinel-1 Synthetic Aperture Radar (SAR) data. A cloud-based image processing framework was developed and implemented in GEE for classification using Random Forest algorithm. The inundation areas due to storm surge owing to cyclone Amphan, were mapped and further categorised to different land use and land cover classes based on an existing land cover map. Sentinel-1 images were useful in post-cyclone studies for the change detection analysis due to its higher temporal resolution and cloud penetration ability. The study found that the majority of agricultural and agricultural fallow lands were inundated in the coastal districts. The availability of open-source cloud-based data processing platforms provides cost effective way to rapidly gather accurate geospatial information. Such information could be useful for emergency response planning and post-event disaster management including relief, rescue and rehabilitation measures; and crop yield loss assessment. Cyclone and Land Use and Land Cover (LULC) change can have significant impacts on the human population and if both coexist, the consequences for people and the surrounding environment may be severe. [ABSTRACT FROM AUTHOR]

This study aims to develop an assumption-free data-driven model to accurately forecast COVID-19 spread. Towards this end, we firstly employed Bayesian optimization to tune the Gaussian process regression (GPR) hyperparameters to develop an efficient GPR-based model for forecasting the recovered and confirmed COVID-19 cases in two highly impacted countries, India and Brazil. However, machine learning models do not consider the time dependency in the COVID-19 data series. Here, dynamic information has been taken into account to alleviate this limitation by introducing lagged measurements in constructing the investigated machine learning models. Additionally, we assessed the contribution of the incorporated features to the COVID-19 prediction using the Random Forest algorithm. Results reveal that significant improvement can be obtained using the proposed dynamic machine learning models. In addition, the results highlighted the superior performance of the dynamic GPR compared to the other models (i.e., Support vector regression, Boosted trees, Bagged trees, Decision tree, Random Forest, and XGBoost) by achieving an averaged mean absolute percentage error of around 0.1%. Finally, we provided the confidence level of the predicted results based on the dynamic GPR model and showed that the predictions are within the 95% confidence interval. This study presents a promising shallow and simple approach for predicting COVID-19 spread. [ABSTRACT FROM AUTHOR]

Purpose: Our objective is to identify the predictive factors and predict hospital length of stay (LOS) in dengue patients, for efficient utilization of hospital resources. Methods: We collected 1360 medical patient records of confirmed dengue infection from 2012 to 2017 at Max group of hospitals in India. We applied two different data mining algorithms, logistic regression (LR) with elastic-net, and random forest to extract predictive factors and predict the LOS. We used an area under the curve (AUC), sensitivity, and specificity to evaluate the performance of the classifiers. Results: The classifiers performed well, with logistic regression (LR) with elastic-net providing an AUC score of 0.75 and random forest providing a score of 0.72. Out of 1148 patients, 364 (32%) patients had prolonged length of stay (LOS) (> 5 days) and overall hospitalization mean was 4.03 ± 2.44 days (median ± IQR). The highest number of dengue cases belonged to the age group of 10-20 years (21.1%) with a male predominance. Moreover, the study showed that blood transfusion, emergency admission, assisted ventilation, low haemoglobin, high total leucocyte count (TLC), low or high haematocrit, and low lymphocytes have a significant correlation with prolonged LOS. Conclusion: Our findings demonstrated that the logistic regression with elastic-net was the best fit with an AUC of 0.75 and there is a significant association between LOS greater than five days and identified patient-specific variables. This method can identify the patients at highest risks and help focus time and resources. [ABSTRACT FROM AUTHOR]