Assessment of groundwater geochemistry for drinking and irrigation suitability in Jaunpur district of Uttar Pradesh using GIS-based statistical inference

The quality of groundwater in the Jaunpur district of Uttar Pradesh is poorly studied despite the fact that it is the only supply of water for both drinking and irrigation and people use it without any pre-treatment. The evaluation of groundwater quality and suitability for drinking and irrigation is presented in this study. Groundwater samples were collected and analysed by standard neutralisation and atomic emission spectrophotometry for major anions (HCO₃^-, SO₄^2-, Cl^-, F^-, NO₃^-), cations (Ca²⁺, Mg²⁺, Na⁺, K⁺), and heavy metals (Cd, Mn, Zn, Cu, and Pb). The geographic information system (GIS) and statistical inferences were utilised for the spatial mapping of the groundwater's parameters. The potential water abstraction (i.e. taking water from sources such as rivers, streams, canals, and underground) for irrigation was assessed using the sodium absorption ratio (SAR), permeability index (PI), residual sodium carbonate (RSC), and Na percentage. According to the findings, the majority of the samples had higher EC, TDS, and TH levels, indicating that they should be avoided for drinking and irrigation. The positive correlation coefficient between chemical variability shows that the water chemistry of the studied region is influenced by geochemical and biological causes. According to the USSL (United States Salinity Laboratory) diagram, most of the samples fall under the C2-S1 and C3-S1 moderate to high salt categories. Some groundwater samples were classified as C4-S3 class which is unfit for irrigation and drinking. This study suggests that the groundwater in the study area is unfit for drinking without treatment. However, the majority of the samples were suitable for irrigation.

Imputation of missing monthly rainfall data using machine learning and spatial interpolation approaches in Thale Sap Songkhla River Basin, Thailand

Missing rainfall data has been a prevalent issue and primarily interested in hydrology and meteorology. This research aimed to examine the capability of machine learning (ML) and spatial interpolation (SI) methods to estimate missing monthly rainfall data. Six ML algorithms (i.e. multiple linear regression (MLR), M5 model tree (M5), random forest (RF), support vector regression (SVR), multilayer perceptron (MLP), genetic programming (GP)) and four SI methods (i.e. arithmetic average (AA), inverse distance weighting (IDW), correlation coefficient weighted (CCW), normal ratio (NR)) were investigated and compared in their performance. The twelve rainfall stations, located in the Thale Sap Songkhla river basin and nearby basins, were considered as a study case. Tuning hyper-parameters for each ML method was conducted to get the most suitable model for the data sets considered. Three performance criteria matrices (i.e. NSE, OI, and r) were chosen, and the sum of those three performance criteria matrices was introduced for methods' performance comparison. The experimental results pointed out that selecting neighbouring stations were essential when applying SI methods, but not for the ML method. The overall performance showed ML better imputed missing monthly rainfall than SI due to overcoming spatial constraints. GP provided the highest performance by giving NSE = 0.825, OI = 0.877, and r = 0.909 for the training stage. Those values for the testing stage were 0.796, 0.852, and 0.902, respectively. It was followed by SVR-rbf, SVR-poly, and RF. NR provided the best performance among four SI methods, followed by CCW, AA, and IDW. When applying SI methods, it should contemplate a correlation between the target and neighbouring stations greater than 0.80.

Association between climate variables and dengue incidence in Nakhon Si Thammarat Province, Thailand

The tropical climate of Thailand encourages very high mosquito densities in certain areas and is ideal for dengue transmission, especially in the southern region where the province Nakhon Si Thammarat is located. It has the longest dengue fever transmission duration that is affected by some important climate predictors, such as rainfall, number of rainy days, temperature and humidity. We aimed to explore the relationship between weather variables and dengue and to analyse transmission hotspots and coldspots at the district-level. Poisson probability distribution of the generalized linear model (GLM) was used to examine the association between the monthly weather variable data and the reported number of dengue cases from January 2002 to December 2018 and geographic information system (GIS) for dengue hotspot analysis. Results showed a significant association between the environmental variables and dengue incidence when comparing the seasons. Temperature, sea-level pressure and wind speed had the highest coefficients, i.e. β=0.17, β= -0.12 and β= -0.11 (P<0.001), respectively. The risk of dengue incidence occurring during the rainy season was almost twice as high as that during monsoon. Statistically significant spatial clusters of dengue cases were observed all through the province in different years. Nabon was identified as a hotspot, while Pak Phanang was a coldspot for dengue fever incidence, explained by the fact that the former is a rubber-plantation hub, while the agricultural plains of the latter lend themselves to the practice of pisciculture combined with rice farming. This information is imminently important for planning apt sustainable control measures for dengue epidemics.

Using machine learning methods for supporting GR2M model in runoff estimation in an ungauged basin

Estimating monthly runoff variation, especially in ungauged basins, is inevitable for water resource planning and management. The present study aimed to evaluate the regionalization methods for determining regional parameters of the rainfall-runoff model (i.e., GR2M model). Two regionalization methods (i.e., regression-based methods and distance-based methods) were investigated in this study. Three regression-based methods were selected including Multiple Linear Regression (MLR), Random Forest (RF), and M5 Model Tree (M5), and two distance-based methods included Spatial Proximity Approach and Physical Similarity Approach (PSA). Hydrological data and the basin's physical attributes were analyzed from 37 runoff stations in Thailand's southern basin. The results showed that using hydrological data for estimating the GR2M model parameters is better than using the basin's physical attributes. RF had the most accuracy in estimating regional GR2M model's parameters by giving the lowest error, followed by M5, MLR, SPA, and PSA. Such regional parameters were then applied in estimating monthly runoff using the GR2M model. Then, their performance was evaluated using three performance criteria, i.e., Nash-Sutcliffe Efficiency (NSE), Correlation Coefficient (r), and Overall Index (OI). The regionalized monthly runoff with RF performed the best, followed by SPA, M5, MLR, and PSA. The Taylor diagram was also used to graphically evaluate the obtained results, which indicated that RF provided the products closest to GR2M's results, followed by SPA, M5, PSA, and MLR. Our finding revealed the applicability of machine learning for estimating monthly runoff in the ungauged basins. However, the SPA would be recommended in areas where lacking the basin's physical attributes and hydrological information.