Portraying urban functional zones provides useful insights into understanding complex urban systems and establishing rational urban planning. Although several studies have confirmed the efficacy of remote sensing imagery in urban studies, coupling remote sensing and new human sensing data like mobile phone positioning data to identify urban functional zones has still not been investigated. In this study, a new framework integrating remote sensing imagery and mobile phone positioning data was developed to analyze urban functional zones with landscape and human activity metrics. Landscapes metrics were calculated based on land cover from remote sensing images. Human activities were extracted from massive mobile phone positioning data. By integrating them, urban functional zones (urban center, sub-center, suburbs, urban buffer, transit region and ecological area) were identified by a hierarchical clustering. Finally, gradient analysis in three typical transects was conducted to investigate the pattern of landscapes and human activities. Taking Shenzhen, China, as an example, the conducted experiment shows that the pattern of landscapes and human activities in the urban functional zones in Shenzhen does not totally conform to the classical urban theories. It demonstrates that the fusion of remote sensing imagery and human sensing data can characterize the complex urban spatial structure in Shenzhen well. Urban functional zones have the potential to act as bridges between the urban structure, human activity and urban planning policy, providing scientific support for rational urban planning and sustainable urban development policymaking.

This study proposed three spectral metrics, namely spectral match degree (SMD), normalized difference mangrove index (NDMI) and shortwave infrared absorption depth (SIAD), to enhance the separability between mangrove forests and terrestrial vegetation in remote sensing imagery. The Landsat 8 OLI image of an interest area in Beilunhekou National Nature Reserve was used to test the spectral metrics. The derived spectral metrics and raw band reflectance data were classified using a support vector machine classifier. Mangrove forest maps were then identified from the classified images. Identification accuracies were compared and evaluated by determining the user’s accuracy (UA), producer’s accuracy (PA), overall accuracy (OA) and by conducting McNemar’s test. Results showed that the use of spectral metrics (UA = 85%, PA = 94%, OA = 95%) outperformed the use of raw band reflectance data (UA = 72%, PA = 82%, OA = 90%). McNemar’s test confirmed that the spectral metrics were significantly better than the raw band reflectance data (Z = 4.63, p < 0.05). Therefore, the proposed spectral metrics could improve the accuracy of mangrove forest identification.

Accurate and up-to-date tidal flat mapping is of much importance to learning how coastal ecosystems work in a time of anthropogenic disturbances and rising sea levels, which will provide scientific instruction for sustainable management and ecological assessments. For large-scale and high spatial-resolution mapping of tidal flats, it is difficult to obtain accurate tidal flat maps without multi-temporal observation data. In this study, we aim to investigate the potential and advantages of the freely accessible Landsat 8 Operational Land Imager (OLI) imagery archive and Google Earth Engine (GEE) for accurate tidal flats mapping. A novel approach was proposed, including multi-temporal feature extraction, machine learning classification using GEE and morphological post-processing. The 50 km buffer of the coastline from Hangzhou Bay to Yalu River in China’s eastern coastal zone was taken as the study area. From the perspective of natural attributes and unexploited status of tidal flats, we delineated a broader extent comprising intertidal flats, supratidal barren flats and vegetated flats, since intertidal flats are major component of the tidal flats. The overall accuracy of the resultant map was about 94.4% from a confusion matrix for accuracy assessment. The results showed that the use of time-series images can greatly eliminate the effects of tidal level, and improve the mapping accuracy. This study also proved the potential and advantage of combining the GEE platform with time-series Landsat images, due to its powerful cloud computing platform, especially for large scale and longtime tidal flats mapping.

The size of phytoplankton not only influences its physiology, metabolic rates and marine food web, but also serves as an indicator of phytoplankton functional roles in ecological and biogeochemical processes. Therefore, some algorithms have been developed to infer the synoptic distribution of phytoplankton cell size, denoted as phytoplankton size classes (PSCs), in surface ocean waters, by the means of remotely sensed variables. This study, using the NASA bio-Optical Marine Algorithm Data set (NOMAD) high performance liquid chromatography (HPLC) database, and satellite match-ups, aimed to compare the effectiveness of modeling techniques, including partial least square (PLS), artificial neural networks (ANN), support vector machine (SVM) and random forests (RF), and feature selection techniques, including genetic algorithm (GA), successive projection algorithm (SPA) and recursive feature elimination based on support vector machine (SVM-RFE), for inferring PSCs from remote sensing data. Results showed that: (1) SVM-RFE worked better in selecting sensitive features; (2) RF performed better than PLS, ANN and SVM in calibrating PSCs retrieval models; (3) machine learning techniques produced better performance than the chlorophyll-a based three-component method; (4) sea surface temperature, wind stress, and spectral curvature derived from the remote sensing reflectance at 490, 510, and 555 nm were among the most sensitive features to PSCs; and (5) the combination of SVM-RFE feature selection techniques and random forests regression was recommended for inferring PSCs. This study demonstrated the effectiveness of machine learning techniques in selecting sensitive features and calibrating models for PSCs estimations with remote sensing.

Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning (DL)-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large, which limits their applicability and explainability, while other models do not make use of the full spectral information in multispectral images, such as Sentinel-2. In this article, we propose a lightweight network for cloud detection, fusing multiscale spectral and spatial features (CD-FM3SFs) and tailored for processing all spectral bands in Sentinel-2A images. The proposed method consists of an encoder and a decoder. In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features. Three novel components are designed: a mixed depthwise separable convolution (MDSC) and a shared and dilated residual block (SDRB) to extract multiscale spatial features, and a concatenation and sum (CS) operation to fuse multiscale spectral and spatial features with little calculation and no additional parameters. The decoder of CD-FM3SF outputs three cloud masks at the same resolution as input bands to enhance the supervision information of small, middle, and large clouds. To validate the performance of the proposed method, we manually labeled 36 Sentinel-2A scenes evenly distributed over mainland China. The experiment results demonstrate that CD-FM3SF outperforms traditional cloud detection methods and state-of-the-art DL-based methods in both accuracy and speed.

Cloud detection is a crucial step in the optical satellite image processing pipeline for Earth observation. Clouds in optical remote sensing images seriously affect the visibility of the background and greatly reduce the usability of images for land applications. Traditional methods based on thresholding, multi-temporal or multi-spectral information are often specific to a particular satellite sensor. Convolutional Neural Networks for cloud detection often require labeled cloud masks for training that are very time-consuming and expensive to obtain. To overcome these challenges, this paper presents a hybrid cloud detection method based on the synergistic combination of generative adversarial networks (GAN) and a physics-based cloud distortion model (CDM). The proposed weakly-supervised GAN-CDM method (available online https://github.com/Neooolee/GANCDM) only requires patch-level labels for training, and can produce cloud masks at pixel-level in both training and testing stages. GAN-CDM is trained on a new globally distributed Landsat 8 dataset (WHUL8-CDb, available online doi:https://doi.org/10.5281/zenodo.6420027) including image blocks and corresponding block-level labels. Experimental results show that the proposed GAN-CDM method trained on Landsat 8 image blocks achieves much higher cloud detection accuracy than baseline deep learning-based methods, not only in Landsat 8 images (L8 Biome dataset, 90.20% versus 72.09%) but also in Sentinel-2 images (“S2 Cloud Mask Catalogue” dataset, 92.54% versus 77.00%). This suggests that the proposed method provides accurate cloud detection in Landsat images, has good transferability to Sentinel-2 images, and can quickly be adapted for different optical satellite sensors.