Wetlands are critical ecosystems that deliver essential services such as water purification, flood regulation, and biodiversity support. Non-intertidal wetlands, in particular, play a key role in maintaining global ecological balance. However, due to their complex structures and dynamic nature, monitoring these ecosystems poses significant challenges. This study offers a comprehensive review of current remote sensing techniques applied to non-intertidal wetlands, with a focus on classification and mapping, vegetation and biodiversity assessment, hydrological monitoring, water quality evaluation, spatiotemporal dynamics, and ecosystem service quantification. We further examine the diverse data sources, analytical models, and technical tools used to monitor these ecosystems. Key challenges identified include limitations in spatial and temporal resolution, ecosystem complexity, and the difficulties of large-scale monitoring. To overcome these barriers, the paper explores promising future directions, including multi-source data integration, the advanced use of hyperspectral satellites, the application of artificial intelligence and machine learning, the coupling of ecological models with socio-economic data, and the development of a global non-intertidal wetland monitoring system. These strategies hold the potential to enhance scientific understanding, support effective conservation efforts, and facilitate sustainable management practices for wetland ecosystems.

High- and very high-resolution (HR, VHR) remote sensing (RS) images can provide comprehensive and intricate spatial information for land cover classification, which is particularly crucial when analyzing complex built-up environments. However, the application of HR and VHR images to large-scale and detailed land cover mapping is always constrained by the intricacy of land cover classification models, the exorbitant cost of collecting training samples, and geographical changes or acquisition conditions. To overcome this limitation, we propose an unsupervised domain adaptation (UDA) with contrastive learning-based discriminative feature augmentation (CLDFA) for RS image classification. In detail, our method first utilizes contrastive learning (CL) through a memory bank in order to memorize sample features and improve model performance, where the approach employs an end-to-end Siamese network and incorporates dynamic pseudo-label assignment and class-balancing strategies for adaptive domain joint learning. By transferring classification models trained on a source domain (SD) to an unlabeled target domain (TD), our proposed UDA method enables large-scale land cover mapping. We conducted experiments using a massive five billion-pixels dataset as the SD and tested the HR and VHR RS images of five typical Chinese cities as the TD and applied the method on the completely unlabeled world view 3 (WV3) image of Urumqi city. The experimental results demonstrate that our method excels in large-scale HR and VHR RS image classification tasks, highlighting the advantages of semantic segmentation based on end-to-end deep convolutional neural networks (DCNNs).

Accurate mapping of wetland vegetation is essential for ecological monitoring and conservation, yet it remains challenging due to the spatial heterogeneity of wetlands, the scarcity of ground-truth data, and the spread of invasive species. Invasive plants alter native vegetation patterns, making their early detection critical for preserving ecosystem integrity. This study proposes a novel framework that integrates self-supervised learning (SSL), supervised segmentation, and multi-sensor data fusion to enhance vegetation classification in the Bayinbuluke Alpine Wetland, China. High-resolution satellite imagery from PlanetScope-3 and Jilin-1 was fused, and SSL methods—including BYOL, DINO, and MoCo v3—were employed to learn transferable feature representations without extensive labeled data. The results show that SSL methods exhibit consistent variations in classification performance, while multi-sensor fusion significantly improves the detection of rare and fragmented vegetation patches and enables the early identification of invasive species. Overall, the proposed SSL–fusion strategy reduces reliance on labor-intensive field data collection and provides a scalable, high-precision solution for wetland monitoring and invasive species management.

Invasive plants (IPs) pose a significant threat to local ecosystems. Recent advances in remote sensing (RS) and deep learning (DL) significantly improved the accuracy of IP detection. However, mainstream DL methods often require large, high-quality labeled data, leading to resource inefficiencies. In this study, a deep learning framework called adversarial positive-unlabeled learning (APUL) was proposed to achieve high-precision IP detection using a limited number of target plant samples. APUL employs a dual-branch discriminator to constrain the class prior-free classifier, effectively harnessing information from positive-unlabeled data through the adversarial process and enhancing the accuracy of IP detection. The framework was tested on very high-resolution Jilin-1 and Sentinel-2 imagery of Bayinbuluke grasslands in Xinjiang, where the invasion of Pedicularis kansuensis has caused serious ecological and livestock damage. Results indicate that the adversarial structure can significantly improve the performance of positive-unlabeled learning (PUL) methods, and the class prior-free approach outperforms traditional PUL methods in IP detection. APUL achieved an overall accuracy of 92.2% and an F1-score of 0.80, revealing that Pedicularis kansuensis has invaded 4.43% of the local plant population in the Bayinbuluke grasslands, underscoring the urgent need for timely control measures.

The expansion of the invasive species Pedicularis kansuensis threatens the ecological integrity of alpine wetlands, particularly in the Bayinbuluke, northwestern China. However, operational monitoring remains challenging. Conventional indices often lack specificity in heterogeneous alpine backgrounds, while deep learning models are typically too data-intensive to support consistent, multi-year mapping. To develop a rapid, reliable, and operational method for monitoring this invader, we proposed a novel, species-specific spectral index, the Pedicularis kansuensis Index (PKI), using the blue, green, and red-edge bands of high-resolution (3 m) PlanetScope imagery. The PKI constructs a robust target signal by integrating distinct spectral features derived from in situ hyperspectral measurement with a grayscale morphological opening (GrMO) refinement to suppress background noise. A comprehensive validation against seven established benchmarks indices (e.g., NDVI, RI, and ARI) demonstrated the superior performance of PKI across the central alpine wetlands of Bayinbuluke (2841 km²). It achieved the highest separability with an M-statistic of 1.36. Furthermore, the index attained an overall accuracy of 93.52% (95% CI: 92.3–94.7%), and an F1-score of 93.28% (95% CI: 92.0–94.5%), effectively minimizing confusion with co-occurring native vegetation and background. Applying this framework to a five-year time series (2021–2025) revealed a distinct cycle of outbreaks and relaxation. Specifically, the invaded area increased to 2168 ha in 2022, then decreased to 160 ha in 2025. Spatial analysis further identified stable invasion hotspots of 161.6 ha, highlighting key targets for long-term containment. Meanwhile, 94.4% of the invaded area was transient, lasting only one year (4824.7 ha). These results confirm that the PKI is a physically interpretable, accurate, and computationally efficient tool for monitoring invasive species in heterogeneous alpine environments. It facilitates timely and targeted ecosystem management.