With continued threat from climate change and human impacts, high-resolution and continuous hydrologic data accessibility has a paramount importance for predicting trends and availability of water resources. This study presents a novel machine learning (ML)-based downscaling algorithm that produces a high spatial resolution groundwater level anomaly (GWLA) from the Gravity Recovery and Climate Experiment (GRACE) data by utilizing the relationship between Terrestrial Water Storage Anomaly (TWSA) from GRACE and other land surface and hydro-climatic variables (e.g., vegetation coverage, land surface temperature, precipitation, streamflow, and in-situ groundwater level data). The predicted downscaled GWLA data were tested using monthly in-situ groundwater level observations. Of the 32 groundwater monitoring wells available in the study site, 21 wells were used to develop the ML-based downscaling model, while the remaining 11 wells were used to assess the performance of the ML-based downscaling model. The test results showed that the model satisfactorily reproduces the spatial and temporal variation of the GWLA in the area, with acceptable correlation coefficient and Nash-Sutcliffe Efficiency values of ~0.76 and ~0.45, respectively. GRACE TWSA was the most influential predictor variable in the models, followed by stream discharge and soil moisture storage. Though model limitations and uncertainty could exist due to high spatial heterogeneity of the geologic materials and omission of human impact (e.g., abstraction), the significance of the result is undeniable, particularly in areas where in-situ well measurements are sparse.

The aim of this study was to investigate the effect of shade screens on the physiological activity, growth parameters and fruit characteristics of the paprika (Capsicum annuum L.) plant. Plants were grown in a protected greenhouse and treated under two different shade screens, S1 (single screen) and S2 (double screens; 10% low light intensity compared to S1), during summer at a particular time of the day. The results revealed that the plant height was significantly enlarged by the S2 treatment. However, the number of leaves, leaf fresh weight and leaf dry weight were significantly decreased under S2-treated plants compared to those grown in the S1 treatment. The stem diameter and shoot fresh weight were not significantly different between the treatments. The sap flow and normalized difference vegetation index (NDVI) were higher in S1-treated plants than in those grown in the S2 treatment. The chlorophyll fluorescence fluctuated in both treatments. The fruit fresh weight, number of fruits, fruit pericarp thickness, fruit firmness, fruit volume, sugar content and acidity were significantly higher in S1-treated plants than in S2. Hunter values a and b were significantly higher in S2-treated plants. Moreover, the fruit length and width were not significantly different between the two treatments. The sugar content and acidity of paprika showed a positive correlation. These results suggest that, compared to a double screen for shade in the greenhouse, a single screen is suitable for the growth of paprika plants and enhanced their fruit production.

Streamflow modeling is essential to investigate processes in the hydrologic cycle and important for water resource management application. However, in-situ hydrologic data paucity because of various factors such as economic, political, instrument malfunctioning, and poor spatial distribution, makes the modeling process challenging. To overcome this limitation, we introduced a satellite remote sensing-based machine learning approach – boosted regression tree (BRT) – that integrates spatial land surface and climate variables that describe the sub-units, and applied it in three variable size watersheds in the Upper Mississippi River Basin (UMRB), USA. The model simulation results were tested using an independent dataset and showed Nash-Sutcliffe efficiency values of 0.80, 0.76, and 0.69 for the UMRB, Illinois River Watershed, and Raccoon River Watershed, respectively. In addition, we compared the performance of the machine learning models with existing process-based modeling results. Overall performance is comparable with the process-based approaches, but with significantly less modeling effort and resources.