Karst regions offer a variety of natural resources such as freshwater and biodiversity, and many cultural resources. The World Karst Aquifer Map (WOKAM) is the first detailed and complete global geodatabase concerning the distribution of karstifiable rocks (carbonates and evaporites) representing potential karst aquifers. This study presents a statistical evaluation of WOKAM, focusing entirely on karst in carbonate rocks and addressing four main aspects: (1) global occurrence and geographic distribution of karst; (2) karst in various topographic settings and coastal areas; (3) karst in different climatic zones; and (4) populations living on karst. According to the analysis, 15.2% of the global ice-free continental surface is characterized by the presence of karstifiable carbonate rock. The largest percentage is in Europe (21.8%); the largest absolute area occurs in Asia (8.35 million km2). Globally, 31.1% of all surface exposures of carbonate rocks occur in plains, 28.1% in hills and 40.8% in mountains, and 151,400 km or 15.7% of marine coastlines are characterized by carbonate rocks. About 34.2% of all carbonate rocks occur in arid climates, followed by 28.2% in cold and 15.9% in temperate climates, whereas only 13.1 and 8.6% occur in tropical and polar climates, respectively. Globally, 1.18 billion people (16.5% of the global population) live on karst. The highest absolute number occurs in Asia (661.7 million), whereas the highest percentages are in Europe (25.3%) and North America (23.5%). These results demonstrate the global importance of karst and serve as a basis for further research and international water management strategies.

No abstract

Abstract. It is now well established to use shallow artificial neural networks (ANNs) to obtain accurate and reliable groundwater level forecasts, which are an important tool for sustainable groundwater management. However, we observe an increasing shift from conventional shallow ANNs to state-of-the-art deep-learning (DL) techniques, but a direct comparison of the performance is often lacking. Although they have already clearly proven their suitability, shallow recurrent networks frequently seem to be excluded from the study design due to the euphoria about new DL techniques and its successes in various disciplines. Therefore, we aim to provide an overview on the predictive ability in terms of groundwater levels of shallow conventional recurrent ANNs, namely non-linear autoregressive networks with exogenous input (NARX) and popular state-of-the-art DL techniques such as long short-term memory (LSTM) and convolutional neural networks (CNNs). We compare the performance on both sequence-to-value (seq2val) and sequence-to-sequence (seq2seq) forecasting on a 4-year period while using only few, widely available and easy to measure meteorological input parameters, which makes our approach widely applicable. Further, we also investigate the data dependency in terms of time series length of the different ANN architectures. For seq2val forecasts, NARX models on average perform best; however, CNNs are much faster and only slightly worse in terms of accuracy. For seq2seq forecasts, mostly NARX outperform both DL models and even almost reach the speed of CNNs. However, NARX are the least robust against initialization effects, which nevertheless can be handled easily using ensemble forecasting. We showed that shallow neural networks, such as NARX, should not be neglected in comparison to DL techniques especially when only small amounts of training data are available, where they can clearly outperform LSTMs and CNNs; however, LSTMs and CNNs might perform substantially better with a larger dataset, where DL really can demonstrate its strengths, which is rarely available in the groundwater domain though.

In this study we investigate how climate change will directly influence the groundwater resources in Germany during the 21st century. We apply a machine learning groundwater level prediction approach based on convolutional neural networks to 118 sites well distributed over Germany to assess the groundwater level development under different RCP scenarios (2.6, 4.5, 8.5). We consider only direct meteorological inputs, while highly uncertain anthropogenic factors such as groundwater extractions are excluded. While less pronounced and fewer significant trends can be found under RCP2.6 and RCP4.5, we detect significantly declining trends of groundwater levels for most of the sites under RCP8.5, revealing a spatial pattern of stronger decreases, especially in the northern and eastern part of Germany, emphasizing already existing decreasing trends in these regions. We can further show an increased variability and longer periods of low groundwater levels during the annual cycle towards the end of the century.

Abstract. It is now well established to use shallow artificial neural networks (ANN) to obtain accurate and reliable groundwater level forecasts, which are an important tool for sustainable groundwater management. However, we observe an increasing shift from conventional shallow ANNs to state-of-the-art deep learning (DL) techniques, but a direct comparison of the performance is often lacking. Although they have already clearly proven their suitability, especially shallow recurrent networks frequently seem to be excluded from the study design despite the euphoria about new DL techniques and its successes in various disciplines. Therefore, we aim to provide an overview on the predictive ability in terms of groundwater levels of shallow conventional recurrent ANN namely nonlinear autoregressive networks with exogenous inputs (NARX), and popular state-of-the-art DL-techniques such as long short-term memory (LSTM) and convolutional neural networks (CNN). We compare both the performance on sequence-to-value (seq2val) and sequence-to-sequence (seq2seq) forecasting on a 4-year period, while using only few, widely available and easy to measure meteorological input parameters, which makes our approach widely applicable. We observe that for seq2val forecasts NARX models on average perform best, however, CNNs are much faster and only slightly worse in terms of accuracy. For seq2seq forecasts, mostly NARX outperform both DL-models and even almost reach the speed of CNNs. However, NARX are the least robust against initialization effects, which nevertheless can be handled easily using ensemble forecasting. We showed that shallow neural networks, such as NARX, should not be neglected in comparison to DL-techniques; however, LSTMs and CNNs might perform substantially better with a larger data set, where DL really can demonstrate its strengths, which is rarely available in the groundwater domain though.