Anthropogenic activities have been significantly perturbing global freshwater flows and groundwater reserves. Despite numerous advances in the development of land surface models (LSMs) and global terrestrial hydrological models (GHMs), relatively few studies have attempted to simulate the impacts of anthropogenic activities on the terrestrial water cycle using the framework of LSMs. From the comparison of simulated terrestrial water storage with the Gravity Recovery and Climate Experiment (GRACE) satellite observations it is found that a process-based LSM, the Minimal Advanced Treatments of Surface Interaction and Runoff (MATSIRO), outperforms the bucket-model-based GHM called H08 in simulating hydrologic variables, particularly in water-limited regions. Therefore, the water regulation modules of H08 are incorporated into MATSIRO. Further, a new irrigation scheme based on the soil moisture deficit is developed. Incorporation of anthropogenic water regulation modules significantly improves river discharge simulation in the heavily regulated global river basins. Simulated irrigation water withdrawal for the year 2000 (2462 km3 yr−1) agrees well with the estimates provided by the Food and Agriculture Organization (FAO). Results indicate that irrigation changes surface energy balance, causing a maximum increase of ~50 W m−2 in latent heat flux averaged over June–August. Moreover, unsustainable anthropogenic water use in 2000 is estimated to be ~450 km3 yr−1, which corresponds well with documented records of groundwater overdraft, representing an encouraging improvement over the previous modeling studies. Globally, unsustainable water use accounts for ~40% of blue water used for irrigation. The representation of anthropogenic activities in MATSIRO makes the model a suitable tool for assessing potential anthropogenic impacts on global water resources and hydrology.

This paper compares different artificial intelligence (AI) models in order to develop the best crop yield prediction model for the Midwestern United States (US). Through experiments to examine the effects of phenology using three different periods, we selected the July–August (JA) database as the best months to predict corn and soybean yields. Six different AI models for crop yield prediction are tested in this research. Then, a comprehensive and objective comparison is conducted between the AI models. Particularly for the deep neural network (DNN) model, we performed an optimization process to ensure the best configurations for the layer structure, cost function, optimizer, activation function, and drop-out ratio. In terms of mean absolute error (MAE), our DNN model with the JA database was approximately 21–33% and 17–22% more accurate for corn and soybean yields, respectively, than the other five AI models. This indicates that corn and soybean yields for a given year can be forecasted in advance, at the beginning of September, approximately a month or more ahead of harvesting time. A combination of the optimized DNN model and spatial statistical methods should be investigated in future work, to mitigate partly clustered errors in some regions.

This paper describes the development of an optimized corn yield prediction model under extreme weather conditions for the Midwestern United States (US). We tested six different artificial intelligence (AI) models using satellite images and meteorological data for the dominant growth period. To examine the effects of extreme weather events, we defined the drought and heatwave by considering the characteristics of corn growth and selected the cases for sensitivity tests from a historical database. In particular, we conducted an optimization for the hyperparameters of the deep neural network (DNN) model to ensure the best configuration for accuracy improvement. The result for drought cases showed that our DNN model was approximately 51–98% more accurate than the other five AI models in terms of root mean square error (RMSE). For the heatwave cases, our DNN model showed approximately 30–77% better accuracy in terms of RMSE. The correlation coefficient was 0.954 for drought cases and 0.887–0.914 for heatwave cases. Moreover, the accuracy of our DNN model was very stable, despite the increases in the duration of the heatwave. It indicates that the optimized DNN model can provide robust predictions for corn yield under conditions of extreme weather and can be extended to other prediction models for various crops in future work.

The worst forest fire in South Korea occurred in April 2000 on the eastern coast. Forest recovery works were conducted until 2005, and the forest has been monitored since the fire. Remote sensing techniques have been used to detect the burned areas and to evaluate the recovery-time point of the post-fire processes during the past 18 years. We used three indices, Normalized Burn Ratio (NBR), Normalized Difference Vegetation Index (NDVI), and Gross Primary Production (GPP), to temporally monitor a burned area in terms of its moisture condition, vegetation biomass, and photosynthetic activity, respectively. The change of those three indices by forest recovery processes was relatively analyzed using an unburned reference area. The selected unburned area had similar characteristics to the burned area prior to the forest fire. The temporal patterns of NBR and NDVI, not only showed the forest recovery process as a result of forest management, but also statistically distinguished the recovery periods at the regions of low, moderate, and high fire severity. The NBR_2.1 for all areas, calculated using 2.1 μm wavelengths, reached the unburned state in 2008. The NDVI for areas with low and moderate fire severity levels became significantly equal to the unburned state in 2009 (p > 0.05), but areas with high severity levels did not reach the unburned state until 2017. This indicated that the surface and vegetation moisture conditions recovered to the unburned state about 8 years after the fire event, while vegetation biomass and health required a longer time to recover, particularly for high severity regions. In the case of GPP, it rapidly recovered after about 3 years. Then, the steady increase in GPP surpassed the GPP of the reference area in 2015 because of the rapid growth and high photosynthetic activity of young forests. Therefore, the concluding scientific message is that, because the recovery-time point for each component of the forest ecosystem is different, using only one satellite-based indicator will not be suitable to understand the post-fire recovery process. NBR, NDVI, and GPP can be combined. Further studies will require more approaches using various terms of indices.

Spectral reflectance-based vegetation indices have sensitive characteristics to crop growth and health conditions. The performance of each vegetation index to a certain condition is different and needs to be interpreted, correspondingly. This study aimed to assess the most suitable vegetation index to identify the crop response against elevated air temperatures, heat stress, and herbicide damage. The spectral reflectance, yield components, and growth parameters such as plant height, leaf area index (LAI), and above-ground dry matter of paddy rice, which was cultivated in a temperature gradient field chamber to simulate global warming conditions, were observed from 2016 to 2018. The relationships between the vegetation indices and the crop parameters were assessed considering stress conditions. The normalized difference vegetation index (NDVI) represented the changes in plant height (R-square = 0.93) and the LAI (R-square = 0.901) before the heading stage. Furthermore, the NDVI and the cumulative growing degree days had a Sigmoid curve and an R-square value of 0.937 under the normal growth case, but it decreased significantly in the herbicide damage case. This characteristic was useful for detecting the damaged crop growth condition. Additionally, to estimate the grain yield of paddy rice, the medium resolution imaging spectrometer (MERIS) terrestrial chlorophyll index was better: R-square = 0.912; root mean square error = 95.69 g/m². Photochemical reflectance index was sensitive to physiological stress caused by the heatwave, and it decreased in response to extremely high air temperatures. These results will contribute towards determining vegetation indices under stress conditions and how to effectively utilize them.

Water supply sources for irrigation (e.g. rivers and reservoirs) are critically important for agricultural productivity. The current rapid increase in irrigation water use is considered unsustainable and threatens food production. In this study, we estimated the time-varying dependence of irrigation water requirements from water supply sources, with a particular focus on variations in irrigation area during past (1960–2001) and future (2002–2050) periods using the global water resources model, H08. The H08 model can simulate water requirements on a daily basis at a resolution of 1.0° × 1.0° latitude and longitude. The sources of irrigation water requirements in the past simulations were specified using four categories: rivers (RIV), large reservoirs (LR) with a storage capacity greater than 1.0 × 10⁹ m³, medium-size reservoirs (MSR) with storage capacities ranging from 1.0 × 10⁹ m³ to 3.0 × 10⁶ m³, and non-local non-renewable blue water (NNBW). The simulated results from 1960 to 2001 showed that RIV, MSR and NNBW increased significantly from the 1960s to the early 1990s globally, but LR increased at a relatively low rate. After the early 1990s, the increase in RIV declined as it approached a critical limit, due to the continued expansion of irrigation area. MSR and NNBW increased significantly, during the same time period, following the expansion of the irrigation area and the increased storage capacity of the medium-size reservoirs. We also estimated future irrigation water requirements from the above four water supply sources and an additional water supply source (ADD) in three future simulation designs; irrigation area change, climate change, and changes in both irrigation area and climate. ADD was defined as a future increase in NNBW. After the 2020s, MSR was predicted to approach the critical limit, and ADD would account for 11–23% of the total requirements in the 2040s.