As the largest freshwater storage in the world, groundwater plays an important role in maintaining ecosystems and helping humans adapt to climate change. However, groundwater dynamics, such as groundwater recharge, cannot be measured directly and is influenced by spatially and temporally complex processes, models are therefore required to capture the dynamics and provide scientific advice for decision-making. This paper developed, estimated and compared the performance of linear regression, multi-layer perception (MLP) and Long Short-Term Memory (LSTM) models in predicting groundwater recharge. The experimental dataset consists of time series of annual recharge from the year 1970 to 2012, based on water table fluctuation estimates from 465 bores in the states of South Australia and Victoria, Australia. We identified the factors that influenced groundwater recharge and found that the correlation between rainfall and groundwater recharge was strongest. The linear regression model had the poorest fitting performance, with the root mean squared error (RMSE) being greater than 0.19 when various proportions of training data were considered. The MLP model outperformed the linear regression in the prediction capability, achieving RMSE = 0.11 when 80% of training data was considered. The LSTM model was found to have the best performance, whose root mean squared errors were less than 0.12 when various proportions of training data were applied. The relative importance of influential predictors was evaluated using the above three models.
22 December 2022 in International Journal of STEM Education
The formation of an academic field is evidenced by many factors, including the growth of relevant research articles and the increasing impact of highly cited publications. Building upon recent scoping reviews of journal publications in STEM education, this study aimed to provide a systematic review of high impact empirical studies in STEM education to gain insights into the development of STEM education research paradigms. Through a search of the Web of Science core database, we identified the top 100 most-cited empirical studies focusing on STEM education that were published in journals from 2000 to 2021 and examined them in terms of various aspects, including the journals where they were published, disciplinary content coverage, research topics and methods, and authorship’s nationality/region and profession. The results show that STEM education continues to gain more exposure and varied disciplinary content with an increasing number of high impact empirical studies published in journals in various STEM disciplines. High impact research articles were mainly authored by researchers in the West, especially the United States, and indicate possible “hot” topics within the broader field of STEM education. Our analysis also revealed the increased participation and contributions from researchers in diverse fields who are working to formulate research agendas in STEM education and the nature of STEM education scholarship.