Quantifying the Relative Contribution of the Climate Change and Human Activity on Runoff in the Choshui River Alluvial Fan, Taiwan

Reconstructing missing time-varying land subsidence data using back propagation neural network with principal component analysis

Land subsidence, a complex geophysical phenomenon, necessitates comprehensive time-varying data to understand regional subsidence patterns over time. This article focuses on the crucial task of reconstructing missing time-varying land subsidence data in the Choshui Delta, Taiwan. We propose a novel algorithm that leverages a multi-factorial perspective to accurately reconstruct the missing time-varying land subsidence data. By considering eight influential factors, our method seeks to capture the intricate interplay among these variables in the land subsidence process. Utilizing Principal Component Analysis (PCA), we ascertain the significance of these influencing factors and their principal components in relation to land subsidence. To reconstruct the absent time-dependent land subsidence data using PCA-derived principal components, we employ the backpropagation neural network. We illustrate the approach using data from three multi-layer compaction monitoring wells from 2008 to 2021 in a highly subsiding region within the study area. The proposed model is validated, and the resulting network is used to reconstruct the missing time-varying subsidence data. The accuracy of the reconstructed data is evaluated using metrics such as root mean square error and coefficient of determination. The results demonstrate the high accuracy of the proposed neural network model, which obviates the need for a sophisticated hydrogeological numerical model involving corresponding soil compaction parameters.

Modelling Runoff within a Small River Basin under the Changing Climate: A Case Study of Using SWAT in the Bălțata River Basin (The Republic of Moldova)

The article focuses on modelling surface runoff in a small river basin taking into consideration climate change projections. The runoff was modelled using the Soil and Water Assessment Tool (SWAT), while three Representative Concentration Pathways (RCP2.6, RCP4.5, and RCP8.5) were considered for modelling the future climate. Despite the identified uncertainties, all the scenarios pointed towards decreasing runoff and losing available water resources. The expected runoff of the case study basin (Bălțata River in the Republic of Moldova) will decrease under all considered scenarios. The risk of diminishing runoff will be low in the middle-term perspective and moderate in the long-term one, if considered from the yearly changes. However, there are months with a high risk of diminishing runoff, especially important for proper crop production. While in the middle-term perspective, traditional adaptation measures can be used, in the long-term one, a totally new approach should be sought.

Linking Spatial–Temporal Changes of Vegetation Cover with Hydroclimatological Variables in Terrestrial Environments with a Focus on the Lake Urmia Basin

Investigation of vegetation cover is crucial to the study of terrestrial ecological environments as it has a close relationship with hydroclimatological variables and plays a dominant role in preserving the characteristics of a region. In Iran, the current study selected the watersheds of two rivers, Nazloo-Chay and Aji-Chay, to systematically investigate the implications and causes of vegetation cover variations under changing environments. These two rivers are among the essential inflows to Lake Urmia, the second largest saline lake on Earth, and are located on the west and east sides of the lake, respectively. There has been a debate between the people living in the rivers’ watersheds about who is responsible for the decline in the level of Lake Urmia—does responsibility fall with those on the east side or with those on the west side? In this study, the normalized difference vegetation index (NDVI) was used as a remotely sensed index to study spatial–temporal pattern changes in vegetation. Moreover, the temperature, precipitation, and streamflow time series were gathered using ground measurements to explore the causes and implications of changing vegetation cover. Discrete wavelet transform was applied to separate the different components of the time series. The Mann–Kendall (MK) test was applied to the time series on monthly, seasonal, and annual time scales. The connections and relationship between the NDVI time series and temperature, precipitation, and streamflow time series and any underlying causes were investigated using wavelet transform coherence (WTC). Land use maps were generated for different years using a support vector machine (SVM) in the final stage. The results indicated that the most dominant monthly, seasonal, and annual hydrological periodicities across the watersheds are 8 months, 6 months, and 2 years, respectively. The increasing vegetation cover during stable hydro-environmental periods revealed unusual conditions in the Aji-Chay watershed and reflected agricultural expansion. The WTC graphs indicated sudden changes in mutual periodicities and time-lags with different patterns between variables, which indicates the increasing anthropogenic activities in both watersheds. However, this was more dominant in the Aji-Chay watershed. The land use maps and investigation of the averaged NDVI maps also denoted that the areas of cultivated land have increased by 30% in the Aji-Chay watershed, and crop types have been changed to the crops with a higher demand for water in both watersheds.