Hualian River is abundant in runoff and high in sediment transport capacity. Most surface water is utilized for agricultural purposes, whereas domestic and industrial water usage relies on the copious amount of available groundwater. To understand the use of water resources in this basin, the fundamental characteristics and recharge of the groundwater need to be analyzed. In this study, the weight of different factors for potential groundwater recharge and the score under various characteristics were assessed based on the characteristics of the study area. A GIS approach was used to integrate five contributing factors: lithology, land cover/land use, lineaments, drainage, and slope. The results demonstrated that about 1.2% of the study area is designated as excellent potential groundwater recharge. Good, moderate and lower potential groundwater recharge areas cover 11.6, 11.7 and 29.9%, respectively; the area with poor potential groundwater recharge covers 45.6%. The results indicate that the most effective groundwater recharge potential zone is located in the Huatung Valley. In this region, the gravelly stratum and the concentration of drainage also help the streamflow recharge the groundwater system

Rice is the most important food crop in Taiwan, directly feeding more than 23 million people in the country. Information on rice production is thus crucial for crop management and food policymaking. This study aims to develop a machine learning (ML) approach for predicting rice crop yields in Taiwan using time-series Moderate Resolution Imaging Spectroradiometer (MODIS) data. We processed the data for the period from 2000 to 2018, following three main steps: (1) data pre-processing to generate smooth time-series Normalized Difference Vegetation Index (NDVI) data, (2) establishment of models for yield predictions using the heading date (HD) NDVI value, and the accumulated NDVI value of the dates from heading to maturity (DHM). The data from 2000 to 2017 were used for building predictive models using the random forests (RF) and support vector machines (SVM), leaving the 2018 data for model assessment, and (3) evaluation of model performance. The results compared with the government’s yield statistics indicated good predictions, with the root mean square error (RMSE) and mean absolute error (MAE) values between 7.1% and 11.8%, and Willmott’s index of agreement (d) values between 0.81 and 0.84 for the first crop, and 5.6% and 11.3% and d values between 0.91 and 0.95 for the second crop, respectively. A slight underestimation of yield predictions was observed for both crops, with the relative error (RE) values of −6.5% to −8.2% and −3.8% to −6% for the first and second crops, respectively. The results of regression analysis also confirmed a close agreement between these two datasets, with the correlation coefficient (r) higher than 0.84 (p-value <0.05), in both cases. Although some factors, including mixed-pixel issues, boundary effects, and cloud cover potentially affected the modelling results, our study demonstrated the effectiveness of ML methods for regional rice yield predictions from MODIS NDVI data in Taiwan.

Landslides have been identified as one of the costliest and deadliest natural disasters, causing tremendous damage to humans and societies. Information regarding the spatial extent of landslides is thus important to allow officials to devise successful strategies to mitigate landslide hazards. This study aims to develop a machine-learning approach for predicting landslide areas in the Tsengwen River Watershed (TRW), which is one of the most landslide-prone areas in Central Taiwan. Various spatial datasets were collected from 2009 to 2015 to derive 36 predictive variables used for landslide modeling with random forests (RF). The results of landslide prediction, compared with ground reference data, indicated an overall accuracy of 91.4% and Kappa coefficient of 0.83, respectively. The findings achieved from estimates of predictor importance also indicated to officials that the land-use/land-cover (LULC) type, distance to previous landslides, distance to roads, bank erosion, annual groundwater recharge, geological line density, aspect, and slope are the most influential factors that trigger landslides in the study region.

Earthquakes, rainfall, or a combination of both can trigger landslides, which can be classified into shallow and deep-seated types according to scale. Landslide risk potential can be charted according to the spatiotemporal characteristics of a combination of triggering factors that can be collated for similar historical events by various methods. The geographic information system (GIS) and the instability index method are two approaches commonly used to perform such a task; however, the nature of the event and the quality of imported data affect the degree of bias of model predictions against real-time values. To identify the differences between shallow and deep-seated landslides, 324 cases of landslides triggered by single rainfall events in Taiwan are analyzed in this study. It is determined that the principal factor governing shallow failure for rainfall-induced landslides is slope and that deep-seated failure is controlled by the amount of accumulated rainfall. By arranging the weighting, these factors could predict 93% and 75% of the occurrences of shallow and deep-seated landslides, respectively, based on a pre-event digital terrain model.

In recent years, increasing drought events due to climate change have led to water scarcity issues in Taiwan, severely impacting the economy and ecosystems. Understanding drought is crucial. This study used Landsat 8 satellite imagery, rainfall, and temperature data to calculate four drought indices, including the Temperature Vegetation Dryness Index (TVDI), improved Temperature Vegetation Dryness Index (iTVDI), Normalized Difference Drought Index (NDDI), and Standardized Precipitation Index (SPI), to investigate spatiotemporal drought variations in the Choushui River Alluvial Fan over the past decade. The findings revealed differences between TVDI and iTVDI in mountainous areas, with iTVDI showing higher accuracy based on soil moisture data. Correlation analysis indicated that drought severity increased with decreasing rainfall or vegetation. The study highlights the significant role of vegetation and precipitation in influencing drought conditions, providing valuable insights for water resource management.