Reliable seasonal prediction of groundwater levels is not always possible when the quality and the amount of available on-site groundwater data are limited. In the present work, a hybrid K-Nearest Neighbor-Random Forest (KNN-RF) is used for the prediction of variations in groundwater levels (L) of an aquifer with the groundwater relatively close to the surface (<10 m) is proposed. First, the time-series smoothing methods are applied to improve the quality of groundwater data. Then, the ensemble K-Nearest Neighbor-Random Forest (KNN-RF) model is treated using hydro-climatic data for the prediction of variations in the levels of the groundwater tables up to three months ahead. Climatic and groundwater data collected from eastern Rwanda were used for validation of the model on a rolling window basis. Potential predictors were: the observed daily mean temperature (T), precipitation (P), and daily maximum solar radiation (S). Previous day’s precipitation P (t − 1), solar radiation S (t), temperature T (t), and groundwater level L (t) showed the highest variation in the fluctuations of the groundwater tables. The KNN-RF model presents its results in an intelligible manner. Experimental results have confirmed the high performance of the proposed model in terms of root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe (NSE), and coefficient of determination (R2).
The rapid expansion of Internet of Things (IoT) devices and applications has accelerated research in various areas of human development. However, the cost of commercial instrumentation impedes the momentum of technological growth in developing regions. In this study, a low-cost, low-power, wireless sensor network for groundwater monitoring (LWNGM) was developed to provide near real-time groundwater level data to support prudent decision making in groundwater resource management in Zanzibar, Tanzania. To facilitate reproducibility, we provided a detailed description of the LWNGM development procedure. The system is based on the ATmega328P microcontroller platform and incorporates low-cost MS5803-14BA and MB280 sensors. To provide a low-power scheme, the Arduino UNO wakes up in six-hour intervals for measurements and data-logging to the SD card, and at twelve-hour intervals for relaying data (in batches) to the LoRa gateway, before it goes back into a deep-sleep mode for the rest of the time (duty cycle<1% ). The average power consumption for the end node across all system cycles was 104.081mW. The power autonomy of all nodes is provided by a 3.7V, 5000mAh rechargeable LiPo battery, and a 9V, 600mAh rechargeable Liion battery, respectively, which are supported by 6V and, 3W solar chargers. The data processing and storage components, as well as the data visualization dashboard, were created using free and open-source software. The LWNGM was reasonably priced, ranging between $350 and $400. The proposed system allows for the adoption of hydrological monitoring, particularly in areas with a limited budget for hydrologic management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.