Groundwater is a crucial natural resource that varies in quality and quantity across Bangladesh. Increased population and urbanization place enormous demands on groundwater supplies, reducing both their quality and quantity. This research aimed to delineate the groundwater potential zone in the Gazipur district, Bangladesh, by integrating eleven thematic layers. Data and information were gathered from Landsat 8, the digital elevation model, the google earth engine, and several ancillary sources. A multi-criterion decision-making (MCDM) based analytical hierarchy process (AHP) was used in a GIS platform to estimate the groundwater potential index. The potential index values were finally classified into five sub-groups: very low, low, moderate, high, and very high to generate a groundwater water potential zone (GWPZ) map. The results show that groundwater potential in about 0.002% (0.026 km²) of the area is very low, 3.83% (63.18 km²) of the area is low, 56.2% (927.05 km²) of the area is medium, 39.25% (647.46 km²) of the area is high, and the rest 0.72% (11.82 km²) of the area is very high. The validation of GWPZ maps based on the groundwater level data at 20 observation wells showed an overall accuracy of 80%. In addition, the ROC curve showed 84% accuracy of GWPZ maps when validated with water inventory points across the study region. Overall, this study presents an easy and practical approach for identifying groundwater potential zones, which may help improve planning and sustainable groundwater resource management.

Drought prediction is the most effective way to mitigate drought impacts. The current study examined the ability of three renowned machine learning models, namely additive regression (AR), random subspace (RSS), and M5P tree, and their hybridized versions (AR-RSS, AR-M5P, RSS-M5P, and AR-RSS-M5P) in predicting the standardized precipitation evapotranspiration index (SPEI) in multiple time scales. The SPEIs were calculated using monthly rainfall and temperature data over 39 years (1980–2018). The best subset regression model and sensitivity analysis were used to determine the most appropriate input variables from a series of input combinations involving up to eight SPEI lags. The models were built at Rajshahi station and validated at four other sites (Mymensingh, Rangpur, Bogra, and Khulna) in drought-prone northern Bangladesh. The findings indicated that the proposed models can accurately forecast droughts at the Rajshahi station. The M5P model predicted the SPEIs better than the other models, with the lowest mean absolute error (27.89–62.92%), relative absolute error (0.39–0.67), mean absolute error (0.208–0.49), root mean square error (0.39–0.67) and highest correlation coefficient (0.75–0.98). Moreover, the M5P model could accurately forecast droughts with different time scales at validation locations. The prediction accuracy was better for droughts with longer periods.

This research intends to design, assemble and evaluate the performance of an eco-friendly solar light trap to reduce the insect population in rice fields as well as to minimize the use of harmful chemical pesticides. An AutoCAD drawing tool 2016 was used to sketch the design of solar light trap. The main component of this light trap was bulb, solar panel and battery. Design of solar panel and battery was done considering by 5W LED bulb. A total of five bulbs with different colors were selected to test the insect’s reaction by visible light. Study indicated that ultra violet-blue bulb showed the best performance compare to others based on the high percentage of insect trap (31.22%). A 20-watt solar panel and two 4.5 ah batteries of 6 volts were used to operate the solar light trap. The current, voltage, solar intensity was recorded to check overall performance of solar panel. The solar panel generated more power in April than May due to higher solar radiation in the study area. Study suggested that only 4.26 sunshine hours were required to full charge the battery. The solar light trap was operated 5.5 hour in night which was sufficient to reduce the insects in rice field. Moreover, the light sensor was showed 100% functional for ON/OFF purposes. The dominant insects like yellow stem borer (YSB), green leafhopper (GLH) were mostly observed. The average largest numbers of YSB and GLH were 900 and 600 respectively. In conclusion, the solar light trap is eco-friendly, low cost, easy and self-sufficient in term of solar energy. Finally, the newly developed light trap could be helpful for manufactures, decision makers, and engineering community as well as farmers as a best tool to protect nature in comparison to other pesticide using practices.