Managing Water Resources Research Articles

Automated Water Regulation Systems for Sustainable Management

Finding new ways to manage water resources becomes even more relevant today, as the growing demand for food globally combines with challenges like climate change and water scarcity. This research paper attempts to discover the automated water regulation systems that utilize advanced technologies like Artificial Intelligence (AI), the Internet of Things (IoT), and data interpretation to upgrade irrigation practices and boost sustainable resource management. By using sensors that keep the soil moisture and the environmental conditions in check, accurate modifications can be made to the irrigation being provided. Keeping a check can help reduce water wastage by up to 30% and increase crop yield by an average of 15%. This study amplifies the productivity of smart meters and the demand for AI-driven prediction models that are capable of providing accurate forecasts and real-time data, both of which are very necessary for efficient water management. However, there exist challenges like the question of data security, high initial costs, and user acceptance. These challenges need to be addressed to make sure that these systems are widely adopted. The considerable potential of the automated water management systems to promote sustainable practices in agriculture and to ensure food security when water scarcity is increasing are highlighted via the findings made in this paper. 1 This paper has been written after taking several research papers written by scholars and professors in this field. Taking into consideration their findings and observations, and incorporating personal observations and the potential results that can be applied, this paper is drafted to recommend practices that will help support vegetation and sustainable practices.

Comparison of Gumbel Method and Log Pearson Method in Flood Control in Konto River Jombang

This study aims to analyze the potential for flooding in the Konto River, Gudo District, Jombang Regency, this study uses the Gumbel and Log Pearson III statistical methods. Floods in this area often occur due to rainwater flow from the surrounding mountains which causes damage to infrastructure and settlements. Maximum daily rainfall data from 2013 to 2023 are used in this analysis. The Gumbel method is a statistical technique that is often used to analyze extreme rainfall data. The Gumbel and Log Pearson III methods are applied to estimate the design rainfall based on the flood return period, which is useful in infrastructure planning and flood mitigation. The calculation results show that the design rainfall increases with the increase in the return period. Compared to the Log Pearson III method, the Gumbel method provides higher design rainfall results, making it more suitable for estimating extreme rainfall in this area. These results are important in efforts to manage water resources and control flooding in the Konto River. The design rainfall will increase with the longer return period. This means that the higher the design rainfall, the smaller the possibility of it happening again. The results of the calculations show that the three methods can be used to calculate the planned rainfall, because the differences between one method and another are not much different, but the most suitable method to use is the gumbell method because the planned rainfall value is greater.

Dynamics of urban development patterns on thermal distributions and their implications on water spread areas of Vellore, Tamil Nadu, India

Recent satellite maps have reported that India is experiencing extreme heat waves, surpassing even Middle Eastern countries. This study addresses a critical gap in understanding how land use land cover (LULC) changes impact land surface temperature (LST), urban heat intensity (UHI), and water spread area (WSA) in rapidly growing cities such as Vellore and Katpadi over three decades (1997–2024). We used Landsat thermal bands and the support vector machine (SVM) algorithm to investigate LULC and LST patterns, examining the effects of urbanization and water body reduction on local climate dynamics. The LULC results showed an increase in built-up lands from 5.89 to 25.89%, while zooming water areas shrank from 3.15 to 1.02%. LST showed a significant increasing trend, with temperatures for water bodies and vegetation ranging from 17.4°C to 26°C, and for barren and built-up areas from 28°C to 42.6°C. The results of the multivariate analysis revealed a positive correlation between LST and the Normalized Difference Built-up Index (NDBI) and negative correlations between LST and the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Water Index (NDWI), and the Modified Normalized Difference Water Index (MNDWI). Moreover, spatial and time series analyses of WSAs indicated a significant increase in LST. Furthermore, a strong negative correlation was found between WSA and LST, with a 10% decrease in WSA potentially increasing LST by 0.12°C to 0.55°C in surrounding regions. This study offers important contributions to improving land use policy and water resource management in urban areas, while addressing environmental concerns related to rising temperatures. The findings underscore the urgency of mitigating heat impacts and managing water resources in rapidly expanding cities. Our results provide valuable insights for policymakers and practitioners aiming to develop more sustainable, resilient, and livable urban environments.

WASTEWATER GLOBAL POLLUTION INDEX AS AN INDICATOR IN ASSESSING THE QUALITY OF THE EFFLUENT FROM THE ARAD MUNICIPAL TREATMENT PLANT

The main aim of the present study was to characterize the quality of the sewage leaving the Arad Municipal Wastewater Treatment Plant and highlight the emergence and importance of water reclamation, recycling, and reuse as vital components in integrated aquatic resources management for further reuse. The sewer quality assessment was performed for the period 2018 - 2021. For this purpose, the Global Pollution Index (𝐼􀯀􀯉 ∗ ) was used to determine the degree of pollution of the wastewater influent and effluent from the Arad treatment plant during the mentioned period. These results on the quality of incoming and outgoing sewerage can contribute to developing a management plan for protecting and properly managing water resources.

A U-Net Model for Urban Land Cover Classification Using VHR Satellite Images

Urban settings are dynamic, constantly changing, and presenting a wide range of surface materials with high diversity in both spatial and spectral variation. As a result, mapping urban growth, evaluating infrastructure, managing water resources, and monitoring natural land cover become more complex tasks. Urban applications have made considerable progress thanks to the abundance of VHR orbital data and the recent development of artificial intelligence strategies especially neural networks. Convolutional neural networks have the potential to significantly enhance the analysis of urban land cover by addressing the limitations of traditional techniques. U-Net is a popular neural network for land cover analysis in remote sensing images. The current research presents a CNN model employing U-Net for image semantic segmentation in urban study area using both spectral and spatial context of VHR satellite data. The proposed model is trained, validated, and tested for VHR satellite image classification into five urban classes: water, vegetation, bare soil, road, and building. The CNN semantic segmentation results are compared to maximum likelihood image classification outcomes for validation and stability evaluation. A confusion matrix is applied to the classified scenes to determine the overall accuracy, producer's and user's accuracy, and Kappa coefficient using 400 random points with their corresponding ground truth. The U-Net image semantic segmentation technique achieved an overall accuracy of 87.50% and Kappa coefficient of 0.8395 which outperforms the maximum likelihood classification method with an overall accuracy of 83.25% and Kappa coefficient of 0.7812.

Optimizing sustainable multiple biomass-to-biofuel conversion network with integrated water resource management utilizing data-driven robust planning

Until now, the biofuel supply chain has lacked an integrated approach to address its fundamental challenges in real-world implementation. The first challenge is maintaining a continuous supply flow in the biofuel network, which can significantly impact economic outcomes and performance measures. The second challenge involves managing water resources for biofuel production to preserve freshwater reserves. The third challenge is managing operational risks, such as uncertainty in biofuel demand, which leads to conservative planning and underscores the need for realistic uncertain programming approaches. To address these challenges, the proposed study designs a biofuel conversion network that utilizes third-generation feedstocks and non-edible seed sources, sourcing necessary water from wastewater resources. This practical solution addresses water-energy relationship concerns, reducing dependency on limited freshwater supplies. To achieve a continuous and cost-effective feed supply, this study incorporates a pre-processing phase using a hybrid Multi-Criteria Decision-Making model. This approach ensures the feed supply remains consistent, economical, and sustainable. To manage the uncertainty in biofuel demand, we developed a robust optimization model with an intersected uncertainty set using a data-driven approach. This approach aims to reduce conservatism in the obtained solutions, making the model more practical for real-world implementation. The numerical results reveal some practical implementation for policymakers. The proposed robust optimization using the configured uncertainty set offers a tool to manage the conservatism of renewable energy demand uncertainty and operational risks more effectively than traditional approaches (0.914%). This formulation can help policymakers to maintain greater robustness against fluctuations in confidence levels. Additionally, the simultaneous use of third-generation and non-edible feedstocks creates a multi-biomass-to-biofuel conversion network, offering practitioners a practical solution that significantly reduces reliance on freshwater resources. Furthermore, policymakers can leverage the proposed pre-processing phase to promote economic and continuous supply feed based on geographical, resource accessibility, and infrastructure criteria.

Are regional groundwater models suitable for simulating wetlands, rivers and intermittence? The example of the French AquiFR platform

Predicting and managing water resources at regional scale under different climate and socio-economic scenarios is crucial to support drinking water supply and other sectors. At the same time, protecting rivers and wetlands from pollutions and droughts is essential and must include groundwater given its contribution to surface water. Yet, assessing temporal and spatial variability of groundwater contributions to surface water is constrained due to limited observations. This study aims to quantify the spatio-temporal distribution of groundwater discharge (hereafter called “GW discharge”) zones, i.e. the groundwater flow to rivers and wetlands, estimated by calibrated regional groundwater flow models (French AquiFR platform). We compare simulation results with two types of surface observations: (i) the spatial distribution of surface water (BD TOPO, RAMSAR and Natura 2000 database) and (ii) an innovative datasets, the river intermittence observed in headwaters (ONDE network). Results show that simulated GW discharge zones are consistent with the observed location of rivers and wetlands. Time variations in GW discharge are well correlated with the intermittence observed at 396 of the 515 selected stations. Of these, groundwater model continues to feed surface water upstream of the station for ∼75 % of observed river drying up events, which may be consistent with a small alluvial flow. The groundwater withdrawals are shown to have a strong impact on the GW discharge and thus on the river intermittence.

Application of major ions and Sr isotopes to indicate the evolution of river water and shallow groundwater chemistry in a typical endorheic watershed, northwestern China

Studying the hydrochemical evolution of river water and groundwater is vital for comprehending complex regional hydrological cycles and managing water resources. An investigation of hydrochemical evolution mechanism of river water and groundwater was executed in an arid and semi-arid endorheic watershed located in the eastern edge of Qaidam Basin, northwest China, by analyzing major ions and strontium isotopic compositions with the combination of hydrogeochemical methods, PMF model and Pearson correlation analysis. From upstream to downstream, the major ions, 87Sr/86Sr values and hydrochemical types of river water and groundwater show spatial variations. Major ions and 87Sr/86Sr analysis reveal that the hydrochmical compositions of river water and groundwater are primarily attributed to silicate weathering, carbonate weathering, evaporite weathering, and agricultural activity. The contribution of four factors affecting the hydrochemical evolution show obvious spatial variations along the flow path. The hydrochemical compositions of river water from the upstream to downstream are mainly contributed by carbonate and silicate weathering as well as weak evaporite weathering (<25%), which are affected by agricultural activity with a great contribution (>25%) in the middle and lower reaches. The contribution to the hydrochemical compositions of groundwater is relatively small (<25%) for carbonate, silicate and evaporite weathering, but great (>25%) for agricultural activity. This study provides implications for understanding the formation and evolution of water and better watershed water management in that typical endorheic watershed basin and even at larger scales.

Water Resources Potential Assessment during Dry Season in Indonesia: A Systematic Literature Review

The dry season in Indonesia has been studied in the context of its impact on rainfall extremes, with research indicating that the dry season rainfall extremes are strongly affected by IOD and ENSO (El Niño-Southern Oscillation). The impact of dry season in 2023 based on the data from the Meteorological, Climatological, and Geophysical Agency (BMKG ) mentioned that this dry season started from march to September 2023. Java Island, whose land area is only 138,379 km² or 7 (seven) percent of Indonesia's area, has a very important position because it is crowded by 65 percent of Indonesia's population or an average of 864 people / km² and contributes to GNP of 60 percent. This article aims to review the water resources in Java Island in Indonesia during the dry season in 2017 to 2023. That causes the lack of water resources has become the main problem in some area in Java Island in Indonesia. This research result assesses the water resources during the dry season, the technique, the method, and the findings. There are 287 articles found only from Scopus sources, 40 article reviewed, and only 5 articles have been matched to the topic by using Prisma P. process. Finally, the result shows that one aspect that remains unclear about Indonesia's dry season is how exactly climate change influences its duration and intensity. While it's known that Indonesia undergoes a dry season, the specific impacts of climate change on factors like rainfall patterns, temperature, and the occurrence of extreme weather events are not fully grasped. This lack of understanding presents challenges for planning agriculture, managing water resources, and conserving ecosystems in the region.

Unraveling Complexity: Exploring Agricultural Systems as Complex Adaptive System with a Focus on the Konya Closed Basin

The study of complex adaptive systems (CAS) has garnered significant attention across interdisciplinary research, particularly within the realms of social and natural sciences. This paper delves into the multifaceted nature of CAS, exploring its definitions, components, and properties, drawing from various scholarly perspectives. It examines the agricultural sector as a prime example of a CAS, highlighting the interactions, adaptations, and emergent behaviors within farming communities. Using the Konya Closed Basin in Türkiye as a case study, the paper elucidates how agricultural landscapes exemplify the complexities inherent in CAS, underscoring the intricate interplay between human activities, environmental dynamics, and socio-economic factors. By recognizing these interactions, decision-makers can create more efficient and resilient strategies for managing water resources, enhancing crop production, and reducing the effects of climate variability. This comprehensive approach emphasizes the role of adaptation, self-organization, and emergent behaviors in promoting sustainable farming practices and maintaining ecological balance over the long term. Through this analysis, the paper contributes to a deeper understanding of CAS and its implications for sustainable agricultural development and resource management.

Enhancing Bright Band Prediction Through RadioSonde RadioWind for International Telecommunication Union- Radio Communications (ITU-R)

As a vital source of information on atmospheric conditions at different altitudes, upper air observations are critical for precise weather forecasting, climate monitoring, and atmospheric research. In coastal areas like Vishakhapatnam that are subject to tropical cyclones and monsoonal fluctuations, radiosondes provide precise vertical profiles that are essential for weather forecasting. They also measure temperature, humidity, and pressure. The addition of wind speed and direction readings via radiowind devices, often known as "rawinsondes," improves severe weather forecasts and our understanding of atmospheric dynamics. Forecasting floods, maintaining aviation safety, and managing water resources are all aided by the ability to predict the bright band, a radar indication of the precipitation layer melting. Weather models and readiness for disasters are much improved in Vishakhapatnam when radiosondes, rawinsondes, and bright band predictions are used in tandem.

Enhancing references evapotranspiration forecasting with teleconnection indices and advanced machine learning techniques

After precipitation, reference evapotranspiration (ETO) plays a crucial role in the hydrological cycle as it quantifies water loss. ETO significantly impacts the water balance and holds great importance at the basin level because of the spatial distribution of managing water resources. Large scale teleconnection indices (LSTIs) play a vital role by influencing climatic variables and can be pivotal in determining ETO and its predictive variables. This study aimed to model and forecast annual ETO in Iran’s basins by utilizing LSTIs and employing various machine learning models (MLMs) such as least squares support vector machine, generalized regression neural network, multi-linear regression (MLR), and multi-layer perceptron (MLP). Initially, climate data from 122 synoptic stations covering six and 30, main and sub basins were collected, and annual ETO values were computed using the Food and Agriculture Organization 56 (PMF 56) Penman–Monteith equation. The correlations between these values and 37 LSTIs were examined within lead times ranging from 7 to 12 months. Through a stepwise approach, the most influential predictor indices (LSTIs) were selected as input datasets for the MLMs. The findings revealed the significant influence of factors such as carbon dioxide (CO2), Atlantic multidecadal oscillation, Atlantic Meridional Mode, and East Atlantic on annual ETO. Overall, all MLMs performed well in terms of the Scatter Index during both training and testing phases across all sub-basins. Furthermore, the MLP and MLR models displayed superior performance compared to other models in the training and testing evaluations based on various assessment metrics.

Panzara River Watershed Prioritization Based on Geomorphometric and LULC Change Analysis using Geo-Spatial Techniques

Human activities can significantly influence the quality of water flowing from a watershed, either positively or negatively. As water moves through the system, these impacts accumulate, with all land-based activities having the potential to affect the water quality and quantity experienced by downstream stakeholders. Similarly, the actions of upstream landowners impact the water that flows across others' properties. Geospatial techniques like remote sensing and geographic information systems (GIS) are invaluable tools for analysing drainage patterns within a watershed and the associated changes in land use and cover. This study focuses on the Panzara river basin, a principal tributary of the larger Tapi river basin, situated in central India between the westward-flowing Godavari and Narmada river systems, which both ultimately discharge into the Arabian Sea. The study area spans latitudes from 20°42'0" N to 21°18'0" N and longitudes from 74°06'0" E to 75°00'0" E, covering a geographical area of 2,986.05 square kilometers with a perimeter of 570.51 kilometers. The watershed delineation was carried out using Shuttle Radar Terrain Mapper (SRTM) data with a 30-meter resolution. For land use and land cover (LULC) analysis, Landsat 5 TM C2L1 and Landsat 8 OLI/TIRS C2L1 datasets, both with 30-meter resolution, were utilized. The present study conducts a morphometric analysis and assesses LULC changes within the Panzara river basin between 2000 and 2021. Morphometric parameters such as linear parameters [Drainage density (Dd), Stream frequency (Fs), Mean bifurcation ratio (Rbm), Drainage texture ratio (Dt), Length of overland flow (Lo)] and areal parameters [Elongation ratio (Re), Circulatory ratio (Cr), Form factor (Rf), Compactness coefficient (Cc)] were used to prioritize sub-watersheds. Furthermore, the study classifies the observed LULC changes between satellite imagery datasets from 2000 and 2021, quantifying the percentage changes in the respective LULC classes across the sub-watersheds over the two decades. The overall accuracy of the LULC classification was 81.82% for 2000 and 88.88% for 2021, with Kappa coefficients of 0.772 and 0.85, respectively. In terms of prioritizing sub-watersheds, common sub- watersheds such as SW-1, SW-10, and SW-15 were classified under moderate priority, while SW-5, SW-8, and SW-14 were classified under the lowest priority. The results of this study, particularly the prioritization of sub-watersheds, can be instrumental for hydraulic engineers in planning and managing water resources in the Panzara river basin.

Implication of Urban Domestic Water Distribution on Human Health in Machakos Central Ward, Machakos County

The world's water resources are running out, and this situation is made worse by how quickly people are populating new areas, particularly in developing nations. This has highlighted the critical requirement for prepared action to manage water resources for sustainable development efficiently. Increasing water demands due to climate change, global pressures from urbanization, the already-existing unsustainable variables, and challenges of water supply systems in urban centres pose a challenge in managing water resource effectively. The purpose of the study was to investigate the implication of urban domestic water supply on human health in Machakos Central Ward, Machakos County. Using a Survey Research Design (SRD) both primary and secondary data was collected by use of questionnaires, face-to-face interviews, photography, use of GIS, authors’ observation, and the review of relevant literature in order to (1) document household water supply, (2) determine water quality for the identified categories of households and domestic water supply systems, and (3) Determine how the distribution and coverage of domestic water in a household or home affects the prevalence of water-borne illnesses. The target population was 8,331 households, from which a sample size of 381 respondents was selected. These included households, water vendors and key informants from the Machakos Water and Sewerage Company. Questionnaires (for households and vendors), interview schedules (for water officers and chiefs) and observation schedules were used as instruments for data collection. Data was analysed using Microsoft Excel and Statistical Package for Social Sciences (SPSS) software. The results revealed that the major factors attributed to lower accessibility are shortage of water, high cost of piped water connection, poor coordination, and participation of stakeholders, repairing of old and broken pipes. As a result, nearly half of the dwellers prefer to use alternative sources, exposing them to the risks of water-born diseases

Application of machine learning and fuzzy AHP for identification of suitable groundwater potential zones using field based hydrogeophysical and soil hydraulic factors in a complex hydrogeological terrain

The eastern section of West Bengal grapples with limited surface water availability in its hard rock terrain, compounded by a semi-arid climate, variable rainfall, and a plateau topography, prompting communities to adapt groundwater water-use practices, leading to unsustainable extraction and misuse. Thus, the novel objective of the present research was to produce groundwater potential maps by comparing machine learning techniques with a Fuzzy MCDM model using specific field-based conditioning factors. In the first step, 285 wells were identified, of which 70 percent were used for training and 30 percent for the validation of the models. Secondly, field-based conditioning factors including, longitudinal conductance (SC), longitudinal resistance (ρl), transverse resistance (TR), coefficient of electrical anisotropy (λ), resistivity of formation (ρm), fracture porosity (φf), reflection coefficients (r), hydraulic conductivity (K), transmissivity(Tr), bulk density, porosity, permeability, soil moisture content and water holding capacity were used to analyze the association between these conditioning factors and groundwater occurrences. In the following steps, the XGBoost, Random Forest, and Naïve Bayes models were executed using the training dataset, and factor weights were calculated using Fuzzy Analytical Hierarchy Process of Extent analysis method. To validate and compare the performance of four models, ROC curves, AUCs, MCAs, and correlation plots were used. In general, all four models were successful in evaluating the potential of groundwater occurrences. The predictive capability of the XGBoost techniques with the highest AUC values (0.79) and the highest correlation value (0.78) is superior to those of other machine learning and MCDM models. Geophysical survey revealed that transmissivity and hydraulic conductivity of the aquifer of the river basin range from 1.55 to 440.11 m/day and 10.15–2253 m2/day, indicating a moderate to good hydrodynamic potential. Planners and engineers can use such groundwater potential maps to manage water resources effectively.

Enhancing water security: Statistical measurement and spatiotemporal analysis

Water security is essential for ensuring energy security, sustainable development, and human survival. However, due to a series of challenges, including rising water demand, environmental pollution, and water resource shortages, the global water security situation remains concerning and poses a threat to global sustainable development. To assess water security in China, this study uses data from 30 provinces in China from 2012 to 2021. A comprehensive evaluation method was applied to determine the level of water resource security in China. The Dagum Gini coefficient, Moran index, and spatial model were used to clarify regional differentiation characteristics and the driving factors. The results indicate that while China's water resource security is relatively low, it has shown steady improvement in recent years. Significant regional disparities exist in water resource security across China, with notable spatial characteristics, and socio-economic factors are the primary causes of these differences. Based on the above research, we put forward policy recommendations from the aspects of water resources management, public participation and inter-regional water resources cooperation, to provide reference for water resources security in developing countries.

Community-led Initiatives for Water Resource Management in Sumenep Regency, Indonesia

Water scarcity is a global issue affecting human health, well-being, and the environment. Community participation is vital to managing water resources, particularly in addressing water scarcity. In Indonesia, East Java is one of the provinces that frequently experiences water shortages. This research explores how local communities manage water resources and utilize local knowledge to address the vulnerability to clean water crises in Desa Parsanga, Sumenep, and East Java. This study employed a qualitative approach using interviews, observations, and document analysis as data collection methods. The research findings revealed that the local community's initiative is demonstrated through their participation in the construction of drilled wells. This participation is facilitated through an organization formed by the local community in Desa Parsanga called the Association of Drinking Water Users (HIPPAM). HIPPAM constructed five drilled wells that supply clean water to approximately 500 households. This initiative demonstrates that the local communityplays a strategic role in water resource management and can promote sustainable practices. This research provides insights into the potential of communities and local knowledge in addressing global water issues.

Evaluating D-InSAR performance to detect small water level fluctuations in two small lakes in Sweden

Monitoring lake water level fluctuations is critical for managing water resources, predicting the impacts of climatic change, and preserving ecosystem services lakes provide. However, traditional gauging stations are insufficient to monitor all lakes worldwide due to the large number of existing lakes, the challenges of installation and maintenance, and the remote locations of some. Although satellite altimetry is an alternative for measuring water levels, it cannot monitor small lakes effectively. This study evaluates the potential of Differential Interferometric Synthetic Aperture Radar (D-InSAR) for tracking minor water level changes in small lakes, a method more typically used in wetland studies. We investigate two Swedish lakes using Sentinel-1A and Sentinel-1B data from 2019, generating six-day interferograms and filtering out those with in situ water level changes exceeding one phase cycle. Our results show that D-InSAR can detect small water level changes with Lin’s correlations up to 0.63 and 0.89 and RMSE values of approximately 9 and 4 mm, respectively. These results evidence the potential of future L-band SAR missions with larger wavelengths, such as the NASA-ISRO SAR (NISAR) of the National Aeronautics and Space Administration (NASA) and the Indian Space Research Organisation (ISRO), to track water level changes in lakes and aid water tracking missions such as the SWOT (Surface Water and Ocean Topography).

Forecasting High Resolution Precipitation Events With Logistic Echo State Networks

AbstractAccurately predicting hydroclimate events is crucial for understanding the impacts of climate change and effectively managing water resources, particularly for flood mitigation and timely warnings. Despite recent advances in machine learning, forecasting precipitation events continues to be challenging due to inherent data imbalances and the intricate dynamics governing these occurrences, rendering them difficult to model accurately. Echo State Networks (ESNs) offer a promising solution; their ability to model complex processes has been demonstrated throughout the field of environmental science. For this work, we propose a novel adaptation of ESNs, termed BinESN, to binary classification problems of precipitation occurrence. In particular, we extend the ESN to a generalized linear model framework, we leverage the ESN's ability to recognize complex dynamics while maintaining interpretability of the predicted output. Through simulation studies and an application to numerically simulated precipitation, we show that BinESN produces more accurate forecasts of sparse events in both short‐ and long‐range scenarios compared to other common machine learning approaches. Specifically, the proposed BinESN outperforms other reference methods by over 10% in terms of its area under the receiver operating characteristic curve.

Geospatial Mapping and Health Status of Some Important Ornamental Fish Habitats of Upper Assam, India

To conserve and manage water resources, it is crucial to create a record of water bodies and their catchments, which can be accomplished through digitized maps. The research focused on five rivers - River Dibru, River Sessa, River Burhidihing, River Brahmaputra, as well as two wetlands of Upper Assam - Maguri Beel, and Mer Beel. These water bodies were chosen based on their abundant fishery resources. Each selected water body was divided into three segments, and one sampling station from each segment was selected for monitoring water quality and recording fish species. The distribution of the catchment area was analyzed in the form of raster maps and geomorphology maps. Based on fish landings, the water bodies were identified and classified, and fish samples were collected through regular field surveys. Over the period from January 2021 to December 2022, eleven physicochemical parameters of the selected water bodies were recorded seasonally to assess the health status of each water bodies. Similarly, the health status and growth coefficient of each fish specimen was done. Water parameters were mostly within the standard limits and demonstrated only a narrow range of seasonal variation. In the studied water bodies, 49 ornamental fish species representing 32 genera under 18 families and 8 orders were found. Among the water bodies, River Dibru had the highest number of ornamental fish species at 46. The order Cypriniformes was dominant in all the studied sites.