The emissions of greenhouse gases, especially CO₂, have been identified as the main contributor for global warming and climate change. Carbon capture and storage (CCS) is considered to be the most promising strategy to mitigate the anthropogenic CO₂ emissions. This review aims to provide the latest developments of CO₂ storage from the perspective of improving safety and economics. The mechanisms and strategies of CO₂ storage, focusing on their characteristics and current status, are discussed firstly. In the second section, the strategies for assessing and ensuring the security of CO₂ storage operations, including the risks assessment approach and monitoring technology associated with CO₂ storage, are outlined. In addition, the engineering methods to accelerate CO₂ dissolution and mineral carbonation for fixing the mobile CO₂ are also compared within the second section. The third part focuses on the strategies for improving economics of CO₂ storage operations, namely enhanced industrial production with CO₂ storage to generate additional profit, and co-injection of CO₂ with impurities to reduce the cost. Moreover, the role of multiple CCS technologies and their distribution on the mitigation of CO₂ emissions in the future are summarized. This review demonstrates that CO₂ storage in depleted oil and gas reservoirs could play an important role in reducing CO₂ emission in the near future and CO₂ storage in saline aquifers may make the biggest contribution due to its huge storage capacity. Comparing the various available strategies, CO₂-enhanced oil recovery (CO₂-EOR) operations are supposed to play the most important role for CO₂ mitigation in the next few years, followed by CO₂-enhanced gas recovery (CO₂-EGR). The direct mineralization of flue gas by coal fly ash and the pH swing mineralization would be the most promising technology for the mineral sequestration of CO₂. Furthermore, by accelerating the deployment of CCS projects on large scale, the government can also play its role in reducing the CO₂ emissions.

Many problems in science and engineering can be mathematically modeled using partial differential equations (PDEs), which are essential for fields like computational fluid dynamics (CFD), molecular dynamics, and dynamical systems. Although traditional numerical methods like the finite difference/element method are widely used, their computational inefficiency, due to the large number of iterations required, has long been a challenge. Recently, deep learning (DL) has emerged as a promising alternative for solving PDEs, offering new paradigms beyond conventional methods. Despite the growing interest in techniques like physics-informed neural networks (PINNs), a systematic review of the diverse neural network (NN) approaches for PDEs is still missing. This survey fills that gap by categorizing and reviewing the current progress of deep NNs (DNNs) for PDEs. Unlike previous reviews focused on specific methods like PINNs, we offer a broader taxonomy and analyze applications across scientific, engineering, and medical fields. We also provide a historical overview, key challenges, and future trends, aiming to serve both researchers and practitioners with insights into how DNNs can be effectively applied to solve PDEs.

Deep Image Manipulation Localization (IML) models suffer from training data insufficiency and thus heavily rely on pre-training. We argue that contrastive learning is more suitable to tackle the data insufficiency problem for IML. Crafting mutually exclusive positives and negatives is the prerequisite for contrastive learning. However, when adopting contrastive learning in IML, we encounter three categories of image patches: tampered, authentic, and contour patches. Tampered and authentic patches are naturally mutually exclusive, but contour patches containing both tampered and authentic pixels are non-mutually exclusive to them. Simply abnegating these contour patches results in a drastic performance loss since contour patches are decisive to the learning outcomes. Hence, we propose the Nonmutually exclusive Contrastive Learning (NCL) framework to rescue conventional contrastive learning from the above dilemma. In NCL, to cope with the non-mutually exclusivity, we first establish a pivot structure with dual branches to constantly switch the role of contour patches between positives and negatives while training. Then, we devise a pivot-consistent loss to avoid spatial corruption caused by the role-switching process. In this manner, NCL both inherits the self-supervised merits to address the data insufficiency and retains a high manipulation localization accuracy. Extensive experiments verify that our NCL achieves state-of-the-art performance on all five benchmarks without any pre-training and is more robust on unseen real-life samples. https://github.com/Knightzjz/NCL-IML.

The mesoscopic level serves as a bridge between the macroscopic and microscopic worlds, addressing gaps overlooked by both. Image manipulation localization (IML), a crucial technique to pursue truth from fake images, has long relied on low-level (microscopic-level) traces. However, in practice, most tampering aims to deceive the audience by altering image semantics. As a result, manipulation commonly occurs at the object level (macroscopic level), which is equally important as microscopic traces. Therefore, integrating these two levels into the mesoscopic level presents a new perspective for IML research. Inspired by this, our paper explores how to simultaneously construct mesoscopic representations of micro and macro information for IML and introduces the Mesorch architecture to orchestrate both. Specifically, this architecture i) combines Transformers and CNNs in parallel, with Transformers extracting macro information and CNNs capturing micro details, and ii) explores across different scales, assessing micro and macro information seamlessly. Additionally, based on the Mesorch architecture, the paper introduces two baseline models aimed at solving IML tasks through mesoscopic representation. Extensive experiments across four datasets have demonstrated that our models surpass the current state-of-the-art in terms of performance, computational complexity, and robustness.