Algal blooms pose a considerable threat to both human health and the natural environment, their presence even extending to lakes situated across plateau regions. The geolocation and volatile climate conditions render it quite a challenge for algal bloom detection with single optical satellite across plateau lakes. To address this limitation, this study aims to achieve algal bloom detection through five satellites with high spatial resolution based on machine learning (ML) across nine lakes in Yunnan Province, China. Noteworthy findings from the study include: 1) achieving high accuracy on algal bloom detection over 0.82 based on random forest (RF) across multiple lakes and multisensors; 2) evaluating quantitatively and qualitatively algal bloom outbreaks in five out of nine plateau lakes in 2019; and 3) establishing a severity ranking of algal bloom occurrences, with Lake Dianchi exhibiting the highest severity, followed by Lake Xingyun, Lake Chenghai, Lake Erhai, and Lake Qilu. In general, this work demonstrated the effectiveness in multisource satellites observation with rational precision. These results laid the foundation for implementing a practical technical framework that enables precise algal bloom detection and facilitates comparative analyses among different lakes.

Earth’s surface is covered by thin-cloud throughout the year, which greatly limits the application of remote sensing (RS) images obtained at a high cost. Currently, deep-learning technology has received widespread attention in the field of thin-cloud removal from RS images. The parameter training process of the deep network in this letter is divided into two stages according to the frequency domain feature of training samples. In the first stage, the loss between the thin-cloud removal image and the corresponding clear image is minimized by the full-frequency domain training. In the second stage, the parameters of the first stage are frozen, and the high-frequency features of the thin-cloud image are integrated into the Decoder module for network training. Furthermore, the corresponding attention module of the dual-tree wavelet is designed. For better training in the second stage, the high-frequency loss function based on three-level wavelet transform is designed. Compared with the highest average values of peak signal to noise ratio (PSNR) and structural similarity (SSIM) of traditional methods, FDT-Net achieves an improvement by up to 33.4108% and 7.5184%, respectively. In quantitative experiments, compared with the highest average values of PSNR and SSIM among deep-learning methods, FDT-Net has an improvement by 2.1505% and 0.9123%, respectively. Therefore, the proposed deep-learning network FDT-Net can significantly extend the temporal and spatial range of RS image application under thin-cloud weather conditions. The code of model is available at https://github.com/chonghaozhan/FDT-Net.

Spectrum sensing with transmit power identification can greatly facilitate the application of the hybrid spectrum access strategy in cognitive radio (CR) networks. Conventional model-driven methods suffer from severe performance degradation in low signal-to-noise ratio (SNR) regime. In this paper, we propose a multiple transmit power levels identification network (TPIN) which consists of three components. In the data preprocessing components, the covariance matrix (COV) of the received data is first employed as the observation data. Then, the residual network (ResNet) based feature extractor components is used to construct the test statistic by extracting high-dimensional features of the observation data. Furthermore, the likelihood ratio test (LRT) criterion is leveraged to design the cost function for obtaining the maximum posterior probability in the classifier components. Different from the assumption in conventional method, the prior probability of each transmit power levels is unknown to the TPIN, and the array of training set is randomly disturbed. In addition, in order to verify the ability of TPIN in data features extraction, a comparison reference experiment using a general test statistic (e.g., higher-order cumulative) as the observation data is introduced. Finally, simulation results demonstrate the identification performance of the COV-based (COV-TPIN) scheme.

At the end of 2019, the very first COVID-19 coronavirus infection was reported and then it spread across the world just like wildfires. From late January to March 2020, most cities and villages in China were locked down, and consequently, human activities decreased dramatically. This letter presents an “offline learning and online inference” approach to explore the variation of PM2.5 pollution during this period. In the experiments, a deep regression model was trained to establish the complex relationship between remote sensing data andin situPM2.5 observations, and then the spatially continuous monthly PM2.5 distribution map was simulated using the Google Earth Engine platform. The results reveal that the COVID-19 lockdown truly decreased the PM2.5 pollution with certain hysteresis and the fine particle pollution begins to increase when advancing resumption of work and production gradually.

Due to the tradeoff between spatial and temporal resolutions of remote sensing images, spatiotemporal fusion models were proposed to synthesize the high spatiotemporal image series. Currently, spatiotemporal fusion models usually employ one coarse-resolution image acquired on a prediction date and at least another pair of coarse–fine resolution images close to the prediction time as references to derive the fine-resolution image on the prediction date. After years of development, the model accuracy has gained a certain improvement, but nearly, all the models require at least three image inputs and rigid time constraints must be applied to the references to guarantee the fusion accuracy. However, it is not always that easy to collect adequate data pairs for fine-resolution image series simulation in practice because of the bad weather condition or the time inconsistency between the coarse–fine resolution data sources, which causes some difficulties in the actual application. This article introduces the conditional generative adversarial network (CGAN) and switchable normalization technique into the spatiotemporal fusion problem and proposes a flexible deep network named the GAN-based SpatioTemporal Fusion Model (GAN-STFM) to reduce the number of model inputs and broke the time restriction on reference image selection. The GAN-STFM just needs a coarse-resolution image on the prediction date and another fine-resolution reference image at an arbitrary time in the same area for model inputs. As far as we know, this is the first spatiotemporal fusion model that requires only two images as model inputs and puts no restriction on the acquisition time of references. Even so, the GAN-STFM performs on par or better than other classical fusion models in the experiments. With this improvement, the data preparation for spatiotemporal fusion tends to be much easier than before, showing a promising perspective for practical applications.

Significant progress has been made in spatiotemporal fusion for remote sensing images; however, most models require inputs to be free of clouds and without missing data, considerably confining their applications in practice. Due to recent advances in deep learning technologies, powerful modeling capabilities could be leveraged to bring potential solutions to this problem. This article proposes a novel architecture named the robust spatiotemporal fusion network (RSFN) based on the generative adversarial network and attention mechanism with dual temporal references to automatically handle input noise. The RSFN only needs one coarse-resolution image on the prediction date and two referential fine-resolution images before and after the prediction date as model inputs. Most notably, there is no special restriction attached on the data quality of referential images. The comparison with other models demonstrates the effectiveness of the RSFN model quantitatively and visually in four study areas using MODIS and Landsat images. Two main conclusions can draw from the experiments. First, the input data noise hardly affects the prediction results of the RSFN, and the RSFN can gain a comparable or even higher accuracy; conversely, the other methods only show limited resistance to input noise. Second, the RSFN with cloud-contaminated references outperforms the other models with cloud-free references after data filtering in the same study area during the same period. The satellite data quality usually varies significantly; the model robustness and fault tolerance are considered critical for actual applications. The RSFN is a simple end-to-end deep model with high accuracy and fault tolerance designed for spatiotemporal fusion with imperfect data inputs, showing promising prospects in practical applications.

Neural networks and tree ensembles are state-of-the-art learners, each with its unique statistical and computational advantages. We aim to combine these advantages by introducing a new layer for neural networks, composed of an ensemble of differentiable decision trees (a.k.a. soft trees). While differentiable trees demonstrate promising results in the literature, they are typically slow in training and inference as they do not support conditional computation. We mitigate this issue by introducing a new sparse activation function for sample routing, and implement true conditional computation by developing specialized forward and backward propagation algorithms that exploit sparsity. Our efficient algorithms pave the way for jointly training over deep and wide tree ensembles using first-order methods (e.g., SGD). Experiments on 23 classification datasets indicate over 10x speed-ups compared to the differentiable trees used in the literature and over 20x reduction in the number of parameters compared to gradient boosted trees, while maintaining competitive performance. Moreover, experiments on CIFAR, MNIST, and Fashion MNIST indicate that replacing dense layers in CNNs with our tree layer reduces the test loss by 7-53% and the number of parameters by 8x. We provide an open-source TensorFlow implementation with a Keras API.

Provenance, the lineage of data products, has been identified as a basic research issue in distributed data and information infrastructures. Provenance could be captured at different levels of granularity. This paper investigates the granularity of provenance for both vector and raster data. In particular, it focuses on the feature and pixel level provenance, and their management in a distributed information environment. The approach is to augment existing geospatial services with provenance awareness. The results show how the provenance with different granularity can be supported in a service-oriented environment enabled by OGC services such as Web Coverage Services, Web Feature Services, Web Processing Services, thus creating a provenance-aware Geo-Cyber infrastructure.