Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In this regard, deep learning is a very promising approach for delineating the non-linear characteristics of drought factors. Therefore, this study aims to monitor drought by employing a deep learning approach with remote sensing data over South Asia from 2001–2016. We considered the precipitation, vegetation, and soil factors for the deep forwarded neural network (DFNN) as model input parameters. The study evaluated agricultural drought using the soil moisture deficit index (SMDI) as a response variable during three crop phenology stages. For a better comparison of deep learning model performance, we adopted two machine learning models, distributed random forest (DRF) and gradient boosting machine (GBM). Results show that the DFNN model outperformed the other two models for SMDI prediction. Furthermore, the results indicated that DFNN captured the drought pattern with high spatial variability across three penology stages. Additionally, the DFNN model showed good stability with its cross-validated data in the training phase, and the estimated SMDI had high correlation coefficient R² ranges from 0.57~0.90, 0.52~0.94, and 0.49~0.82 during the start of the season (SOS), length of the season (LOS), and end of the season (EOS) respectively. The comparison between inter-annual variability of estimated SMDI and in-situ SPEI (standardized precipitation evapotranspiration index) showed that the estimated SMDI was almost similar to in-situ SPEI. The DFNN model provides comprehensive drought information by producing a consistent spatial distribution of SMDI which establishes the applicability of the DFNN model for drought monitoring.

The identification and early warning of potential landslides can effectively reduce the number of casualties and the amount of property loss. At present, interferometric synthetic aperture radar (InSAR) is considered one of the mainstream methods for the large-scale identification and detection of potential landslides, and it can obtain long-term time-series surface deformation data. However, the method of identifying anomalous deformation areas using InSAR data is still mainly manual delineation, which is time-consuming, labor-consuming, and has no generally accepted criterion. In this study, a two-stage detection deep learning network (InSARNet) is proposed and used to detect anomalous deformation areas in Maoxian County, Sichuan Province. Compared with the most commonly used detection models, it is demonstrated that the InSARNet has a better performance in the detection of anomalous deformation in mountainous areas, and all of the quantitative evaluation indexes are higher for InSARNet than for the other models. After the anomalous deformation areas are identified using the proposed model, the possible relationship between the anomalous deformation areas and potential landslides is investigated. Finally, the fact that the automatic and rapid identification of potential landslides is the inevitable trend of future development is discussed.

Carbon Capture, Utilization and Storage, also referred to as Carbon Capture, Utilization and Sequestration (CCUS), is one of the novel climate mitigation technologies by which CO₂ emissions are captured from sources, such as fossil power generation and industrial processes, and further either reused or stored with more attention being paid on the utilization of captured CO₂. In the whole CCUS process, the dominant migration pathway of CO₂ after being injected underground becomes very important information to judge the possible storage status as well as one of the essential references for evaluating possible environmental affects. Interferometric Synthetic Aperture Radar (InSAR) technology, with its advantages of extensive coverage in surface deformation monitoring and all-weather traceability of the injection processes, has become one of the promising technologies frequently adopted in worldwide CCUS projects. In this study, taking the CCUS sequestration area in Shizhuang Town, Shanxi Province, China, as an example, unmanned aerial vehicle (UAV) photography measurement technology with a 3D surface model at a resolution of 5.3 cm was applied to extract the high-resolution digital elevation model (DEM) of the study site in coordination with InSAR technology to more clearly display the results of surface deformation monitoring of the CO₂ injection area. A 2 km surface heaving dynamic processes before and after injection from June 2020 to July 2021 was obtained, and a CO₂ migration pathway northeastward was observed, which was rather consistent with the monitoring results by logging and micro-seismic studies. Additionally, an integrated monitoring scheme, which will be the trend of monitoring in the future, is proposed in the discussion.

Carbon neutrality is a goal the world is striving to achieve in the context of global warming. Carbon capture and storage (CCS) has received extensive attention as an effective method to reduce carbon dioxide (CO₂) in the atmosphere. What follows is the migration pathway and leakage monitoring after CO₂ injection. Interferometric synthetic aperture radar (InSAR) technology, with its advantages of extensive coverage in surface deformation monitoring and all-weather traceability of the injection processes, has become one of the promising technologies frequently adopted in worldwide CCS projects. However, there is no mature evaluation system to determine whether InSAR technology is suitable for each CO₂ sequestration area. In this study, a new evaluation model is proposed based on the eight factors that are selected from the principle of the InSAR technique and the unique characteristics of the CO₂ sequestration area. According to the proposed model, the feasibility of InSAR monitoring is evaluated for the existing typical sequestration areas in the world. Finally, the challenges and prospects of InSAR in the CCS project are discussed.

With satellite observed Sea Surface Temperature (SST) accumulated for multiple decades, multi-time scale variabilities of the Indo-Pacific Warm Pool are examined and contrasted in this study by separating it into the Indian Ocean sector and the Pacific Ocean sector. Surface size, zonal center, meridional center, maximum SST and mean SST as the practical warm pool properties are chosen to investigate the warm pool variations for the period 1982–2018. On the seasonal time scale, the oscillation of the Indian Warm Pool is found much more vigorous than the Pacific Warm Pool on size and intensity, yet the interannual variabilities of the Indian Warm Pool and the Pacific Warm Pool are comparable. The Indian Warm Pool has weak interannual variations (3–5 years) and the Pacific Warm Pool has mighty interdecadal variations. The size, zonal movement and mean SST of the Indian Ocean Warm Pool (IW) are more accurate to depict the seasonal variability, and for the Pacific Ocean Warm Pool (PW), the size, zonal and meridional movements and maximum SST are more suitable. On the interannual scale, except for the meridional movements, all the other properties of the same basin have similar interannual variation signals. Following the correlation analysis, it turns out that the Indian Ocean basin-wide index (IOBW) is the most important contributor to the variabilities of both sectors. Lead-lag correlation results show that variation of the Pacific Ocean Warm Pool leads the IOBW and variation of the Indian Ocean Warm Pool is synchronous with the IOBW. This indicates that both sectors of the Indo-Pacific Warm Pool are significantly correlated with basin-wide warming or cooling.

Terrestrial ecosystems in China are threatened by land use and future climate change. Understanding the effects of these changes on vegetation and the climate-vegetation interactions is critical for vegetation preservation and mitigation. However, land-use impacts on vegetation are neglected in terrestrial ecosystems exploration, and a deep understanding of land-use impacts on vegetation dynamics is lacking. Additionally, few studies have examined the contribution of vegetation succession to changes in vegetation dynamics. To fill the above gaps in the field, the spatiotemporal distribution of terrestrial ecosystems under the current land use and climate baseline (1970–2000) was examined in this study using the Comprehensive Sequential Classification System (CSCS) model. Moreover, the spatiotemporal variations of ecosystems and their succession under future climate scenarios (the 2030s–2080s) were quantitatively projected and compared. The results demonstrated that under the current situation, vegetation without human disturbance was mainly distributed in high elevation regions and less than 10% of the national area. For future vegetation dynamics, more than 58% of tundra and alpine steppe would shrink. Semidesert would respond to climate change with an expansion of 39.49 × 10⁴ km², including the succession of the steppe to semidesert. Although some advancement of the temperate forest at the expense of substantial dieback of tundra and alpine steppe is expected to occur, this century would witness a considerable shrinkage of them, especially in RCP8.5, at approximately 55.06 × 10⁴ km². Overall, a warmer and wetter climate would be conducive to the occurrence and development of the CSCS ecosystems. These results offer new insights on the potential ecosystem response to land use and climate change over the Chinese domain, and on creating targeted policies for effective adaptation to these changes and implementation of ecosystem protection measures.