Search

The transmission of high-frequency signals over long distances depends on the ionosphere's reflective properties, with the selection of operating frequencies being closely tied to variations in the ionosphere. The accurate prediction of ionospheric critical frequency foF2 and other parameters in low latitudes is of great significance for understanding ionospheric changes in high-frequency communications. Currently, deep learning algorithms demonstrate significant advantages in capturing characteristics of the ionosphere. In this paper, a state-of-the-art hybrid neural network is utilized in conjunction with a temporal pattern attention mechanism for predicting variations in the foF2 parameter during high- and low-solar activity years. Convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM), which is capable of extracting spatiotemporal features of ionospheric variations, are incorporated into a hybrid neural network. The foF2 data used for training and testing come from three observatories in Brisbane (27°53′S, 152°92′E), Darwin (12°45′S, 130°95′E) and Townsville (19°63′S, 146°85′E) in 2000, 2008, 2009 and 2014 (the peak or trough years of solar activity in solar cycles 23 and 24), using the advanced Australian Digital Ionospheric Sounder. The results show that the proposed model accurately captures the changes in ionospheric foF2 characteristics and outperforms International Reference Ionosphere 2020 (IRI-2020) and BiLSTM ionospheric prediction models. [ABSTRACT FROM AUTHOR]

The new generation of available (i.e., PRISMA, ENMAP, DESIS) and future (i.e., ESA-CHIME, NASA-SBG) spaceborne hyperspectral missions provide unprecedented data for environmental and agricultural monitoring, such as crop trait assessment. This paper focuses on retrieving two crop traits, specifically Chlorophyll and Nitrogen content at the canopy level (CCC and CNC), starting from hyperspectral images acquired during the CHIME-RCS project, exploiting a self-supervised learning (SSL) technique. SSL is a machine learning paradigm that leverages unlabeled data to generate valuable representations for downstream tasks, bridging the gap between unsupervised and supervised learning. The proposed method comprises pre-training and fine-tuning procedures: in the first stage, a de-noising Convolutional Autoencoder is trained using pairs of noisy and clean CHIME-like images; the pre-trained Encoder network is utilized as-is or fine-tuned in the second stage. The paper demonstrates the applicability of this technique in hybrid approach methods that combine Radiative Transfer Modelling (RTM) and Machine Learning Regression Algorithm (MLRA) to set up a retrieval schema able to estimate crop traits from new generation space-born hyperspectral data. The results showcase excellent prediction accuracy for estimating CCC (R2 = 0.8318; RMSE = 0.2490) and CNC (R2 = 0.9186; RMSE = 0.7908) for maize crops from CHIME-like images without requiring further ground data calibration. [ABSTRACT FROM AUTHOR]

The accurate estimation of forest aboveground biomass is of great significance for forest management and carbon balance monitoring. Remote sensing instruments have been widely applied in forest parameters inversion with wide coverage and high spatiotemporal resolution. In this paper, the capability of different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 and Landsat-8) and various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), in aboveground forest biomass estimation. In particular, based on the forest inventory data of Hangzhou in China, the Random Forest (RF), Convolutional Neural Network (CNN) and Convolutional Neural Networks Long Short-Term Memory Networks (CNN-LSTM) algorithms were deployed to construct the forest biomass estimation models, respectively. The estimate accuracies were evaluated under the different configurations of images and methods. The results show that for the SAR data, ALOS-2 has a higher biomass estimation accuracy than the GaoFen-3 and Sentinel-1. Moreover, the GaoFen-6 data is slightly worse than Sentinel-2 and Landsat-8 optical data in biomass estimation. In contrast with the single source, integrating multisource data can effectively enhance accuracy, with improvements ranging from 5% to 10%. The CNN-LSTM generally performs better than CNN and RF, regardless of the data used. The combination of CNN-LSTM and multisource data provided the best results in this case and can achieve the maximum R2 value of up to 0.74. It was found that the majority of the biomass values in the study area in 2018 ranged from 60 to 90 Mg/ha, with an average value of 64.20 Mg/ha. [ABSTRACT FROM AUTHOR]

Ship detection has been an area of focus for high-frequency surface wave radar (HFSWR). The detection and identification of ship formation have proven significant in early warning, while studies on the formation identification are limited due to the complex background and low resolution of HFSWR. In this paper, we first establish a spatial distribution model of ship formation in HFSWR. Then, we propose a cascade identification algorithm of ship formation in the clutter edge. The proposed algorithm includes a preprocessing stage and a two-stage formation identification stage. The Faster R-CNN is introduced in the preprocessing stage to locate the clutter regions. In the first stage, we propose an extremum detector based on connected regions to extract suspicious regions. The suspicious regions contain ship formations, single-ship targets, and false targets. In the second stage, we design a network connected by a convolutional neural network (CNN) and an extreme learning machine (ELM) to identify two densely distributed ship formations from inhomogeneous clutter and single-ship targets. The experimental results based on the factual HFSWR background demonstrate that the proposed cascade identification algorithm is superior to the extremum detector combined with the classical CNN algorithm for ship formation identification. Meanwhile, the proposed algorithm performs well in weak formation and deformed formation identification. [ABSTRACT FROM AUTHOR]

In the field of image fusion, spatial detail blurring and color distortion appear in synthetic aperture radar (SAR) images and multispectral (MS) during the traditional fusion process due to the difference in sensor imaging mechanisms. To solve this problem, this paper proposes a fusion method for SAR images and MS images based on a convolutional neural network. In order to make use of the spatial information and different scale feature information of high-resolution SAR image, a dual-channel feature extraction module is constructed to obtain a SAR image feature map. In addition, different from the common direct addition strategy, an attention-based feature fusion module is designed to achieve spectral fidelity of the fused images. In order to obtain better spectral and spatial retention ability of the network, an unsupervised joint loss function is designed to train the network. In this paper, the Sentinel 1 SAR images and Landsat 8 MS images are used as datasets for experiments. The experimental results show that the proposed algorithm has better performance in quantitative and visual representation when compared with traditional fusion methods and deep learning algorithms. [ABSTRACT FROM AUTHOR]

Geological hazards often occur in mountainous areas and are sudden and hidden, so it is important to identify and assess geological hazards. In this paper, the western mountainous area of Beijing was selected as the study area. We conducted research on landslides, collapses, and unstable slopes in the study area. The surface deformation of the study area was monitored by multi-temporal interferometric synthetic aperture radar (MT-InSAR), using a combination of multi-looking point selection and permanent scatterer (PS) point selection methods. Random forest (RF), support vector machine (SVM), convolutional neural network (CNN), and recurrent neural network (RNN) models were selected for the assessment of geological hazard susceptibility. Sixteen geological hazard-influencing factors were collected, and their information values were calculated using their features. Multicollinearity analysis with the relief-F method was used to calculate the correlation and importance of the factors for factor selection. The results show that the deformation rate along the line-of-sight (LOS) direction is between −44 mm/year and 28 mm/year. A total of 60 geological hazards were identified by combining surface deformation with optical imagery and other data, including 7 collapses, 25 unstable slopes, and 28 landslides. Forty-eight of the identified geological hazards are not recorded in the Beijing geological hazards list. The most effective model in the study area was RF. The percentage of geological hazard susceptibility zoning in the study area is as follows: very low susceptibility 27.40%, low susceptibility 28.06%, moderate susceptibility 21.19%, high susceptibility 13.80%, very high susceptibility 9.57%. [ABSTRACT FROM AUTHOR]

Automatic target recognition (ATR) algorithms are used to classify a given synthetic aperture radar (SAR) image into one of the known target classes by using the information gleaned from a set of training images that are available for each class. Recently, deep learning methods have been shown to achieve state-of-the-art classification accuracy if abundant training data are available, especially if they are sampled uniformly over the classes and in their poses. In this paper, we consider the ATR problem when a limited set of training images are available. We propose a data-augmentation approach to incorporate SAR domain knowledge and improve the generalization power of a data-intensive learning algorithm, such as a convolutional neural network (CNN). The proposed data-augmentation method employs a physics-inspired limited-persistence sparse modeling approach, which capitalizes on the commonly observed characteristics of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we fit over-parametrized models of scattering to limited training data, and use the estimated models to synthesize new images at poses and sub-pixel translations that are not available in the given data in order to augment the limited training data. We exploit the sparsity of the scattering centers in the spatial domain and the smoothly varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of the over-parametrized model fitting. The experimental results show that, for the training on the data-starved regions, the proposed method provides significant gains in the resulting ATR algorithm's generalization performance. [ABSTRACT FROM AUTHOR]

With increasing access to open spatial data, it is possible to improve the quality of analyses carried out in the preliminary stages of the investment process. The extraction of buildings from raster data is an important process, especially for urban, planning and environmental studies. It allows, after processing, to represent buildings registered on a given image, e.g., in a vector format. With an actual image it is possible to obtain current information on the location of buildings in a defined area. At the same time, in recent years, there has been huge progress in the use of machine learning algorithms for object identification purposes. In particular, the semantic segmentation algorithms of deep convolutional neural networks which are based on the extraction of features from an image by means of masking have proven themselves here. The main problem with the application of semantic segmentation is the limited availability of masks, i.e., labelled data for training the network. Creating datasets based on manual labelling of data is a tedious, time consuming and capital-intensive process. Furthermore, any errors may be reflected in later analysis results. Therefore, this paper aims to show how to automate the process of data labelling of cadastral data from open spatial databases using convolutional neural networks, and to identify and extract buildings from high resolution orthophotomaps based on this data. The conducted research has shown that automatic feature extraction using semantic ML segmentation on the basis of data from open spatial databases is possible and can provide adequate quality of results. [ABSTRACT FROM AUTHOR]

Oil spills on the sea surface have caused serious harm to the marine ecological environment and coastal environment. Oil film thickness (OFT) is an important parameter for estimating oil spills amount, and accurate quantification of OFT is of great significance for rapid response and risk assessment of oil spills. In recent years, thermal infrared remote sensing has been gradually applied to quantify the OFT. In this paper, the outdoor oil spill simulation experiments were designed, and the bright temperature (BT) data of different OFTs were obtained for 24 consecutive hours in summer and autumn. On the basis of the correlation analysis of OFT and bright temperature difference (BTD) between oil and water, the traditional regression fitting model, classical machine learning model, ensemble learning model, and deep learning model were applied to the inversion of OFT. At the same time, inversion results of the four models were compared and analyzed. In addition, the best OFT inversion time using thermal infrared was studied based on 24-h thermal infrared data. Additionally, the inversion results were compared with the measured results; the optimal OFT range detectable using thermal infrared was explored. The experimental results show that: (1) Compared with ensemble learning model, traditional regression fitting model, and classical machine learning model, Convolutional Neural Network (CNN) has the advantages of high stability while maintaining high-precision inversion, and can be used as the preferred model for oil film thickness inversion; (2) The optimal time for OFT detection is around 10:00 to 13:00 of the day, and is not affected by seasonal changes; (3) During the day, thermal infrared has good detection ability for OFT greater than 0.4 mm, and weak detection ability for thinner oil films; (4) At night, thermal infrared has certain detection ability for relatively thick oil film, but the accuracy is lower than that in the daytime. [ABSTRACT FROM AUTHOR]

Reliable and timely crop-yield prediction and crop mapping are crucial for food security and decision making in the food industry and in agro-environmental management. The global coverage, rich spectral and spatial information and repetitive nature of remote sensing (RS) data have made them effective tools for mapping crop extent and predicting yield before harvesting. Advanced machine-learning methods, particularly deep learning (DL), can accurately represent the complex features essential for crop mapping and yield predictions by accounting for the nonlinear relationships between variables. The DL algorithm has attained remarkable success in different fields of RS and its use in crop monitoring is also increasing. Although a few reviews cover the use of DL techniques in broader RS and agricultural applications, only a small number of references are made to RS-based crop-mapping and yield-prediction studies. A few recently conducted reviews attempted to provide overviews of the applications of DL in crop-yield prediction. However, they did not cover crop mapping and did not consider some of the critical attributes that reveal the essential issues in the field. This study is one of the first in the literature to provide a thorough systematic review of the important scientific works related to state-of-the-art DL techniques and RS in crop mapping and yield estimation. This review systematically identified 90 papers from databases of peer-reviewed scientific publications and comprehensively reviewed the aspects related to the employed platforms, sensors, input features, architectures, frameworks, training data, spatial distributions of study sites, output scales, evaluation metrics and performances. The review suggests that multiple DL-based solutions using different RS data and DL architectures have been developed in recent years, thereby providing reliable solutions for crop mapping and yield prediction. However, challenges related to scarce training data, the development of effective, efficient and generalisable models and the transparency of predictions should be addressed to implement these solutions at scale for diverse locations and crops. [ABSTRACT FROM AUTHOR]

Global solar photovoltaic capacity has consistently doubled every 18 months over the last two decades, going from 0.3 GW in 2000 to 643 GW in 2019, and is forecast to reach 4240 GW by 2040. However, these numbers are uncertain, and virtually all reporting on deployments lacks a unified source of either information or validation. In this paper, we propose, optimize, and validate a deep learning framework to detect and map solar farms using a state-of-the-art semantic segmentation convolutional neural network applied to satellite imagery. As a final step in the pipeline, we propose a model to estimate the energy generation capacity of the detected solar energy facilities. Objectively, the deep learning model achieved highly competitive performance indicators, including a mean accuracy of 96.87%, and a Jaccard Index (intersection over union of classified pixels) score of 95.5%. Subjectively, it was found to detect spaces between panels producing a segmentation output at a sub-farm level that was better than human labeling. Finally, the detected areas and predicted generation capacities were validated against publicly available data to within an average error of 4.5% Deep learning applied specifically for the detection and mapping of solar farms is an active area of research, and this deep learning capacity evaluation pipeline is one of the first of its kind. We also share an original dataset of overhead solar farm satellite imagery comprising 23,000 images (256 × 256 pixels each), and the corresponding labels upon which the machine learning model was trained. [ABSTRACT FROM AUTHOR]

Field seed maturity monitoring is essential to optimize the farming process and guarantee yield quality through high germination. Remote sensing of parsley fields through UAV multispectral imagery allows uniform scanning and better capture of crop information, in comparison to traditional limited field sampling analysis in the laboratory. Moreover, they only represent localized sub-sections of the crop field and are time consuming to process. The limited availability of seed sample maturity data is a drawback for applying deep learning methods, which have shown tremendous potential in estimating agronomic parameters, especially maturity, as they require large labeled datasets. In this paper, we propose a parametric and non-parametric-based weak labeling approach to overcome the lack of maturity labels and render possible maturity estimation by deep network regression to assist growers in harvest decision-making. We present the data acquisition protocol and the performance evaluation of the generative models and neural network architectures. Convolutional and recurrent neural networks were trained on the generated labels and evaluated on maturity ground truth labels to assess the maturity quantification quality. The results showed improvement by the semi-supervised approaches over the generative models, with a root-mean-squared error of 0.0770 for the long-short-term memory network trained on kernel-density-estimation-generated labels. Generative-model-based data labeling can unlock new possibilities for remote sensing fields where data collection is complex, and in our usage, they provide better-performing models for parsley maturity estimation based on UAV multispectral imagery. [ABSTRACT FROM AUTHOR]

Most of the existing Non-Cooperative Target Recognition (NCTR) systems follow the "closed world" assumption, i.e., they only work with what was previously observed. Nevertheless, the real world is relatively "open" in the sense that the knowledge of the environment is incomplete. Therefore, unknown targets can feed the recognition system at any time while it is operational. Addressing this issue, the Openmax classifier has been recently proposed in the optical domain to make convolutional neural networks (CNN) able to reject unknown targets. There are some fundamental limitations in the Openmax classifier that can end up with two potential errors: (1) rejecting a known target and (2) classifying an unknown target. In this paper, we propose a new classifier to increase the robustness and accuracy. The proposed classifier, which is inspired by the limitations of the Openmax classifier, is based on proportional similarity between the test image and different training classes. We evaluate our method by radar images of man-made targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. Moreover, a more in-depth discussion on the Openmax hyper-parameters and a detailed description of the Openmax functioning are given. [ABSTRACT FROM AUTHOR]

The noise radiated from ships can be used for their identification and classification using passive sonar systems. Several techniques have been proposed for military ship classification based on acoustic signatures, which can be acquired through controlled experiments performed in an acoustic lane. The cost for such data acquisition is a significant issue since the ship and crew have to be dislocated from the fleet. In addition, the experiments have to be repeated for different operational conditions, taking a considerable amount of time. Even with this massive effort, the scarce amount of data produced by these controlled experiments may limit further detailed analyses. In this paper, deep learning models are used for full exploitation of such acquired data, envisaging passive sonar signal classification. A drawback of such models is the large number of parameters, which requires extensive data volumes for parameter tuning along the training phase. Thus, generative adversarial networks (GANs) are used to synthesize data so that a larger data volume can be produced for training convolutional neural networks (CNNs), which are used for the classification task. Different GAN design approaches were evaluated and both maximum probability and class-expert strategies were exploited for signal classification. Special attention was paid to how the expert knowledge might give a handle on analyzing the performance of the various deep learning models through tests that mirrored actual deployment. An accuracy as high as 99.0 ± 0.4 % was achieved using experimental data, which improves upon previous machine learning designs in the field. [ABSTRACT FROM AUTHOR]

In recent years, hyperspectral image (HSI) classification (HSIC) methods that use deep learning have proved to be effective. In particular, the utilization of convolutional neural networks (CNNs) has proved to be highly effective. However, some key issues need to be addressed when classifying hyperspectral images (HSIs), such as small samples, which can influence the generalization ability of the CNNs and the HSIC results. To address this problem, we present a new network that integrates hybrid pyramid feature fusion and coordinate attention for enhancing small sample HSI classification results. The innovative nature of this paper lies in three main areas. Firstly, a baseline network is designed. This is a simple hybrid 3D-2D CNN. Using this baseline network, more robust spectral-spatial feature information can be obtained from the HSI. Secondly, a hybrid pyramid feature fusion mechanism is used, meaning that the feature maps of different levels and scales can be effectively fused to enhance the feature extracted by the model. Finally, coordinate attention mechanisms are utilized in the network, which can not only adaptively capture the information of the spectral dimension, but also include the direction-aware and position sensitive information. By doing this, the proposed CNN structure can extract more useful HSI features and effectively be generalized to test samples. The proposed method was shown to obtain better results than several existing methods by experimenting on three public HSI datasets. [ABSTRACT FROM AUTHOR]

We present a machine-learning approach to detect and analyze meteor echoes (MADAME), which is a radar data processing workflow featuring advanced machine-learning techniques using both supervised and unsupervised learning. Our results demonstrate that YOLOv4, a convolutional neural network (CNN)-based one-stage object detection model, performs remarkably well in detecting and identifying meteor head and trail echoes within processed radar signals. The detector can identify more than 80 echoes per minute in the testing data obtained from the Jicamarca high power large aperture (HPLA) radar. MADAME is also capable of autonomously processing data in an interferometer mode, as well as determining the target's radiant source and vector velocity. In the testing data, the Eta Aquarids meteor shower could be clearly identified from the meteor radiant source distribution analyzed automatically by MADAME, thereby demonstrating the proposed algorithm's functionality. In addition, MADAME found that about 50 percent of the meteors were traveling in inclined and near-inclined circular orbits. Furthermore, meteor head echoes with a trail are more likely to originate from shower meteor sources. Our results highlight the capability of advanced machine-learning techniques in radar signal processing, providing an efficient and powerful tool to facilitate future and new meteor research. [ABSTRACT FROM AUTHOR]

There has been substantial progress in small object detection in aerial images in recent years, due to the extensive applications and improved performances of convolutional neural networks (CNNs). Typically, traditional machine learning algorithms tend to prioritize inference speed over accuracy. Insufficient samples can cause problems for convolutional neural networks, such as instability, non-convergence, and overfitting. Additionally, detecting aerial images has inherent challenges, such as varying altitudes and illuminance situations, and blurred and dense objects, resulting in low detection accuracy. As a result, this paper adds a transformer backbone attention mechanism as a branch network, using the region-wide feature information. This paper also employs a generative model to expand the input aerial images ahead of the backbone. The respective advantages of the generative model and transformer network are incorporated. On the dataset presented in this study, the model achieves 96.77% precision, 98.83% recall, and 97.91% m A P by adding the Multi-GANs module to the one-stage detection network. These three indices are enhanced by 13.9%, 20.54%, and 10.27%, respectively, when compared to the other detection networks. Furthermore, this study provides an auto-pruning technique that may achieve 32.2 FPS inference speed with a minor performance loss while responding to the real-time detection task's usage environment. This research also develops a macOS application for the proposed algorithm using Swift development technology. [ABSTRACT FROM AUTHOR]

Due to device limitations, small networks are necessary for some real-world scenarios, such as satellites and micro-robots. Therefore, the development of a network with both good performance and small size is an important area of research. Deep networks can learn well from large amounts of data, while manifold networks have outstanding feature representation at small sizes. In this paper, we propose an approach that exploits the advantages of deep networks and shallow Grassmannian manifold networks. Inspired by knowledge distillation, we use the information learned from convolutional neural networks to guide the training of the manifold networks. Our approach leads to a reduction in model size, which addresses the problem of deploying deep learning on resource-limited embedded devices. Finally, a series of experiments were conducted on four remote sensing scene classification datasets. The method in this paper improved the classification accuracy by 2.31% and 1.73% on the UC Merced Land Use and SIRIWHU datasets, respectively, and the experimental results demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) shows great potential for application in remote sensing due to its rich spectral information and fine spatial resolution. However, the high dimensionality, nonlinearity, and complex relationship between spectral and spatial features of HSI pose challenges to its accurate classification. Traditional convolutional neural network (CNN)-based methods suffer from detail loss in feature extraction; Transformer-based methods rely too much on the quantity and quality of HSI; and graph neural network (GNN)-based methods provide a new impetus for HSI classification by virtue of their excellent ability to handle irregular data. To address these challenges and take advantage of GNN, we propose a network of parallel GNNs called PGNN-Net. The network first extracts the key spatial-spectral features of HSI using principal component analysis, followed by preprocessing to obtain two primary features and a normalized adjacency matrix. Then, a parallel architecture is constructed using improved GCN and ChebNet to extract local and global spatial-spectral features, respectively. Finally, the discriminative features obtained through the fusion strategy are input into the classifier to obtain the classification results. In addition, to alleviate the over-fitting problem, the label smoothing technique is embedded in the cross-entropy loss function. The experimental results show that the average overall accuracy obtained by our method on Indian Pines, Kennedy Space Center, Pavia University Scene, and Botswana reaches 97.35%, 99.40%, 99.64%, and 98.46%, respectively, which are better compared to some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We propose a new convolutional neural networks method in combination with ordinal regression aiming at assessing the degree of building damage caused by earthquakes with aerial imagery. The ordinal regression model and a deep learning algorithm are incorporated to make full use of the information to improve the accuracy of the assessment. A new loss function was introduced in this paper to combine convolutional neural networks and ordinal regression. Assessing the level of damage to buildings can be considered as equivalent to predicting the ordered labels of buildings to be assessed. In the existing research, the problem has usually been simplified as a problem of pure classification to be further studied and discussed, which ignores the ordinal relationship between different levels of damage, resulting in a waste of information. Data accumulated throughout history are used to build network models for assessing the level of damage, and models for assessing levels of damage to buildings based on deep learning are described in detail, including model construction, implementation methods, and the selection of hyperparameters, and verification is conducted by experiments. When categorizing the damage to buildings into four types, we apply the method proposed in this paper to aerial images acquired from the 2014 Ludian earthquake and achieve an overall accuracy of 77.39%; when categorizing damage to buildings into two types, the overall accuracy of the model is 93.95%, exceeding such values in similar types of theories and methods. [ABSTRACT FROM AUTHOR]

Grapevine rootstocks are gaining importance in viticulture as a strategy to combat abiotic challenges, as well as enhance scion physiology. Direct leaf-level physiological parameters like net assimilation rate, stomatal conductance to water vapor, quantum yield of PSII, and transpiration can illuminate the rootstock effect on scion physiology. However, these measures are time-consuming and limited to leaf-level analysis. This study used different rootstocks to investigate the potential application of aerial hyperspectral imagery in the estimation of canopy level measurements. A statistical framework was developed as an ensemble stacked regression (REGST) that aggregated five different individual machine learning algorithms: Least absolute shrinkage and selection operator (Lasso), Partial least squares regression (PLSR), Ridge regression (RR), Elastic net (ENET), and Principal component regression (PCR) to optimize high-throughput assessment of vine physiology. In addition, a Convolutional Neural Network (CNN) algorithm was integrated into an existing REGST, forming a hybrid CNN-REGST model with the aim of capturing patterns from the hyperspectral signal. Based on the findings, the performance of individual base models exhibited variable prediction accuracies. In most cases, Ridge Regression (RR) demonstrated the lowest test Root Mean Squared Error (RMSE). The ensemble stacked regression model (REGST) outperformed the individual machine learning algorithms with an increase in R2 by (0.03 to 0.1). The performances of CNN-REGST and REGST were similar in estimating the four different traits. Overall, these models were able to explain approximately 55–67% of the variation in the actual ground-truth data. This study suggests that hyperspectral features integrated with powerful AI approaches show great potential in tracing functional traits in grapevines. [ABSTRACT FROM AUTHOR]

Glacier inventories are fundamental in understanding glacier dynamics and glacier-related environmental processes. High-resolution mapping of glacier outlines is lacking, although high-resolution satellite images have become available in recent decades. Challenges in development of glacier inventories have always included accurate delineation of boundaries of debris-covered glaciers, which is particularly true for high-resolution satellite images due to their limited spectral bands. To address this issue, we introduced an automated, high-precision method in this study for mapping debris-covered glaciers based on 1 m resolution Gaofen-2 (GF-2) imagery. By integrating GF-2 reflectance, topographic features, and land surface temperature (LST), we used an attention mechanism to improve the performance of several deep learning network models (the U-Net network, a fully convolutional neural network (FCNN), and DeepLabV3+). The trained models were then applied to map the outlines of debris-covered glaciers, at 1 m resolution, in the central Karakoram regions. The results indicated that the U-Net model enhanced with the Convolutional Block Attention Module (CBAM) outperforms other deep learning models (e.g., FCNN, DeepLabV3+, and U-Net model without CBAM) in terms of precision for supraglacial debris identification. On the testing dataset, the CBAM-enhanced U-Net model achieved notable performance metrics, with its accuracy, F1 score, mean intersection over union (MIoU), and kappa coefficient reaching 0.93, 0.74, 0.79, and 0.88. When applied at the regional scale, the model even exhibits heightened precision (accuracies = 0.94, F1 = 0.94, MIoU = 0.86, kappa = 0.91) in mapping debris-covered glaciers. The experimental glacier outlines were accurately extracted, enabling the distinction of supraglacial debris, clean ice, and other features on glaciers in central Karakoram using this trained model. The results for our method revealed differences of 0.14% for bare ice and 10.36% against the manually interpreted glacier boundary for supraglacial debris. Comparison with previous glacier inventories revealed raised precisions of 8.74% and 4.78% in extracting clean ice and with supraglacial debris, respectively. Additionally, our model demonstrates exceptionally high exclusion for bare rock outside glaciers and could reduce the influence of non-glacial snow on glacier delineation, showing substantial promise in mapping debris-covered glaciers. [ABSTRACT FROM AUTHOR]

Earth observation imaging technologies, particularly multispectral sensors, produce extensive high-dimensional data over time, thus offering a wealth of information on global dynamics. These data encapsulate crucial information in essential climate variables, such as varying levels of soil moisture and temperature. However, current cutting-edge machine learning models, including deep learning ones, often overlook the treasure trove of multidimensional data, thus analyzing each variable in isolation and losing critical interconnected information. In our study, we enhance conventional convolutional neural network models, specifically those based on the embedded temporal convolutional network framework, thus transforming them into models that inherently understand and interpret multidimensional correlations and dependencies. This transformation involves recasting the existing problem as a generalized case of N-dimensional observation analysis, which is followed by deriving essential forward and backward pass equations through tensor decompositions and compounded convolutions. Consequently, we adapt integral components of established embedded temporal convolutional network models, like encoder and decoder networks, thus enabling them to process 4D spatial time series data that encompass all essential climate variables concurrently. Through the rigorous exploration of diverse model architectures and an extensive evaluation of their forecasting prowess against top-tier methods, we utilize two new, long-term essential climate variables datasets with monthly intervals extending over four decades. Our empirical scrutiny, particularly focusing on soil temperature data, unveils that the innovative high-dimensional embedded temporal convolutional network model-centric approaches markedly excel in forecasting, thus surpassing their low-dimensional counterparts, even under the most challenging conditions characterized by a notable paucity of training data. [ABSTRACT FROM AUTHOR]

Ground-penetrating radar (GPR) faces complex challenges in identifying underground rock formations and lithological structures. The diversity, intricate shapes, and electromagnetic properties of subsurface rock formations make their accurate detection difficult. Additionally, the heterogeneity of subsurface media, signal scattering, and non-linear propagation effects contribute to the complexity of signal interpretation. To address these challenges, this study fully considers the unique advantages of convolutional neural networks (CNNs) in accurately identifying underground rock formations and lithological structures, particularly their powerful feature extraction capabilities. Deep learning models possess the ability to automatically extract complex signal features from radar data, while also demonstrating excellent generalization performance, enabling them to handle data from various geological conditions. Moreover, deep learning can efficiently process large-scale data, thereby improving the accuracy and efficiency of identification. In our research, we utilized deep neural networks to process GPR signals, using radar images as inputs and generating structure-related information associated with rock formations and lithological structures as outputs. Through training and learning, we successfully established an effective mapping relationship between radar images and lithological label signals. The results from synthetic data indicate a rock block identification success rate exceeding 88%, with a satisfactory continuity identification of lithological structures. Transferring the network to measured data, the trained model exhibits excellent performance in predicting data collected from the field, further enhancing the geological interpretation and analysis. Therefore, through the results obtained from synthetic and measured data, we can demonstrate the effectiveness and feasibility of this research method. [ABSTRACT FROM AUTHOR]

Enhancing the reliability of inversion results has always been a prominent issue in the field of geophysics. In recent years, data-driven inversion methods leveraging deep neural networks (DNNs) have gained prominence for their ability to address non-uniqueness issues and reduce computational costs compared to traditional physically model-driven methods. In this study, we propose a GMNet machine learning method, i.e., a CNN-based inversion method for gravity and magnetic field data. This method relies more on data-driven training, and in the prediction phase after the model is trained, it does not heavily depend on a priori assumptions, unlike traditional methods. By forward modeling gravity and magnetic fields, we obtain a substantial dataset to train the CNN model, enabling the direct mapping from field data to subsurface property distribution. Applying this method to synthetic data and one-field data yields promising inversion results. [ABSTRACT FROM AUTHOR]

We present an evaluation of different deep learning and machine learning approaches for tree health classification in the Black Forest, the Harz Mountains, and the Göttinger Forest on a unique, highly accurate tree-level dataset. The multispectral UAV data were collected from eight forest plots with diverse tree species, mostly conifers. As ground truth data (GTD), nearly 1500 tree polygons with related attribute information on the health status of the trees were used. This data were collected during extensive fieldwork using a mobile application and subsequent individual tree segmentation. Extensive preprocessing included normalization, NDVI calculations, data augmentation to deal with the underrepresented classes, and splitting the data into training, validation, and test sets. We conducted several experiments using a classical machine learning approach (random forests), as well as different convolutional neural networks (CNNs)—ResNet50, ResNet101, VGG16, and Inception-v3—on different datasets and classes to evaluate the potential of these algorithms for tree health classification. Our first experiment was a binary classifier of healthy and damaged trees, which did not consider the degree of damage or tree species. The best results of a 0.99 test accuracy and an F1 score of 0.99 were obtained with ResNet50 on four band composites using the red, green, blue, and infrared bands (RGBI images), while VGG16 had the worst performance, with an F1 score of only 0.78. In a second experiment, we also distinguished between coniferous and deciduous trees. The F1 scores ranged from 0.62 to 0.99, with the highest results obtained using ResNet101 on derived vegetation indices using the red edge band of the camera (NDVIre images). Finally, in a third experiment, we aimed at evaluating the degree of damage: healthy, slightly damaged, and medium or heavily damaged trees. Again, ResNet101 had the best performance, this time on RGBI images with a test accuracy of 0.98 and an average F1 score of 0.97. These results highlight the potential of CNNs to handle high-resolution multispectral UAV data for the early detection of damaged trees when good training data are available. [ABSTRACT FROM AUTHOR]

This study investigates the potential of Sentinel-1 (S1) multi-temporal data for the early-season mapping of the rapeseed crop. Additionally, we explore the effectiveness of limiting the portion of a considered time series to map rapeseed fields. To this end, we conducted a quantitative analysis to assess several temporal windows (periods) spanning different phases of the rapeseed phenological cycle in the following two scenarios relating to the availability or constraints of providing ground samples for different years: (i) involving the same year for both training and the test, assuming the availability of ground samples for each year; and (ii) evaluating the temporal transferability of the classifier, considering the constraints of ground sampling. We employed two different classification methods that are renowned for their high performance in land cover mapping: the widely adopted random forest (RF) approach and a deep learning-based convolutional neural network, specifically the InceptionTime algorithm. To assess the classification outcomes, four evaluation metrics (recall, precision, F1 score, and Kappa) were employed. Using S1 time series data covering the entire rapeseed growth cycle, the tested algorithms achieved F1 scores close to 95% on same-year training and testing, and 92.0% when different years were used, both algorithms demonstrated robust performance. For early rapeseed detection within a two-month window post-sowing, RF and InceptionTime achieved F1 scores of 67.5% and 77.2%, respectively, and 79.8% and 88.9% when extended to six months. However, in the context of temporal transferability, both classifiers exhibited mean F1 scores below 50%. Notably, a 5-month time series, covering key growth stages such as stem elongation, inflorescence emergence, and fruit development, yielded a mean F1 score close to 95% for both algorithms when trained and tested in the same year. In the temporal transferability scenario, RF and InceptionTime achieved mean F1 scores of 92.0% and 90.0%, respectively, using a 5-month time series. Our findings underscore the importance of a concise S1 time series for effective rapeseed mapping, offering advantages in data storage and processing time. Overall, the study establishes the robustness of RF and InceptionTime in rapeseed detection scenarios, providing valuable insights for agricultural applications. [ABSTRACT FROM AUTHOR]

Remote sensing image segmentation with samples imbalance is always one of the most important issues. Typically, a high-resolution remote sensing image has the characteristics of high spatial resolution and low spectral resolution, complex large-scale land covers, small class differences for some land covers, vague foreground, and imbalanced distribution of samples. However, traditional machine learning algorithms have limitations in deep image feature extraction and dealing with sample imbalance issue. In the paper, we proposed an improved full-convolution neural network, called DeepLab V3+, with loss function based solution of samples imbalance. In addition, we select Sentinel-2 remote sensing images covering the Yuli County, Bayingolin Mongol Autonomous Prefecture, Xinjiang Uygur Autonomous Region, China as data sources, then a typical region image dataset is built by data augmentation. The experimental results show that the improved DeepLab V3+ model can not only utilize the spectral information of high-resolution remote sensing images, but also consider its rich spatial information. The classification accuracy of the proposed method on the test dataset reaches 97.97%. The mean Intersection-over-Union reaches 87.74%, and the Kappa coefficient 0.9587. The work provides methodological guidance to sample imbalance correction, and the established data resource can be a reference to further study in the future. [ABSTRACT FROM AUTHOR]

Geographic object-based image analysis (GEOBIA) is a remote sensing image analysis paradigm that defines and examines image-objects: groups of neighboring pixels that represent real-world geographic objects. Recent reviews have examined methodological considerations and highlighted how GEOBIA improves upon the 30+ year pixel-based approach, particularly for H-resolution imagery. However, the literature also exposes an opportunity to improve guidance on the application of GEOBIA for novice practitioners. In this paper, we describe the theoretical foundations of GEOBIA and provide a comprehensive overview of the methodological workflow, including: (i) software-specific approaches (open-source and commercial); (ii) best practices informed by research; and (iii) the current status of methodological research. Building on this foundation, we then review recent research on the convergence of GEOBIA with deep convolutional neural networks, which we suggest is a new form of GEOBIA. Specifically, we discuss general integrative approaches and offer recommendations for future research. Overall, this paper describes the past, present, and anticipated future of GEOBIA in a novice-accessible format, while providing innovation and depth to experienced practitioners. [ABSTRACT FROM AUTHOR]

There are an estimated 800,000 small reservoirs globally with a range of uses. Given the collective importance of these reservoirs to water resource management and wider society, it is essential that we can monitor and understand the hydrological dynamics of ungauged reservoirs, particularly in a changing climate. However, unlike large reservoirs, continuous and systematic hydrological observations of small reservoirs are often unavailable. In response, this study has developed a retrieval framework for water levels of small reservoirs using a deep learning algorithm and remotely sensed satellite data. Demonstrated at four reservoirs in California, satellite imagery from both Sentinel-1 and Sentinel-2 along with corresponding water level field measurements was collected. Post-processed images were fed into a water level inversion convolutional neural network model for water level inversion, while different combinations of these satellite images, sampling approaches for training/testing data, and attention modules were used to train the model and evaluated for accuracy. The results show that random sampling of training data coupled with Sentinel-2 satellite imagery was generally the most accurate initially. Performance is improved by incorporating a channel attention mechanism, with the average R2 increasing by 8.6% and the average RMSE and MAE decreasing by 15.5% and 36.4%, respectively. The proposed framework was further validated on three additional reservoirs in different regions. In conclusion, the retrieval framework proposed in this study provides a stable and accurate methodology for water level estimation of small reservoirs and can be a powerful tool for small reservoir monitoring over large spatial scales. [ABSTRACT FROM AUTHOR]

The estimate of precipitation from satellite measurements is an indirect estimate if compared to rain gauges or disdrometer measurements, but it has the advantage of complete coverage over oceans, mountainous regions, and sparsely populated areas where other sources of precipitation data (e.g., weather radar) are unavailable or unreliable. Among the satellite-based precipitation estimates, geostationary (GEO) data ensure the highest spatial and temporal resolution. At the same time, the IR/VIS channels deployed on GEO satellites have lower capabilities than microwave (MW) channels in characterizing the cloud structure. Machine learning (ML) techniques can be considered a powerful tool to overcome the limitations related to the physical relationship between IR/VIS channels and precipitation estimation. This study describes the development of a convolutional neural network (U-Net) to retrieve the precipitation rate using IR measurements only from the Meteosat Second Generation (MSG) satellite. Its performances are evaluated through a comparison with H SAF and NASA operational products (e.g., H60B or H03B and IMERG-E, respectively), of which the algorithms are based on different principles. The results highlight a lower error in precipitation rate estimates for the U-Net with respect to the other products but also some issues in correctly estimating the more intense precipitation (>5 mmh−1). On the other hand, the precipitation detection capabilities of the U-Net outperform the H SAF products for lower precipitation rate, while IMERG-E shows the best performance regardless of the precipitation regime. Furthermore, the U-Net is able to account for and correct the parallax displacement that affects the measurement as the satellite viewing angle increases. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is significant for landslide risk assessment. However, there remains no consensus on which method is optimal for LSM. This study implements a dynamic approach to landslide hazard mapping by integrating spatio-temporal probability analysis with time-varying ground deformation velocity derived from the MT-InSAR (Multi-Temporal InSAR) method. Reliable landslide susceptibility maps (LSMs) can inform landslide risk managers and government officials. First, sixteen factors were selected to construct a causal factor system for LSM. Next, Pearson correlation analysis, multicollinearity analysis, information gain ratio, and GeoDetector methods were applied to remove the least important factors of STI, plan curvature, TRI, and slope length. Subsequently, information quantity (IQ), logistic regression (LR), frequency ratio (FR), artificial neural network (ANN), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) methods were performed to construct the LSM. The results showed that the distance to a river, slope angle, distance from structure, and engineering geological rock group were the main factors controlling landslide development. A comprehensive set of statistical indicators was employed to evaluate these methods' effectiveness; sensitivity, F1-measure, and AUC (area under the curve) were calculated and subsequently compared to assess the performance of the methods. Machine learning methods' training and prediction accuracy were higher than those of statistical methods. The AUC values of the IQ, FR, LR, BP-ANN, RBF-ANN, RF, SVM, and CNN methods were 0.810, 0.854, 0.828, 0.895, 0.916, 0.932, 0.948, and 0.957, respectively. Although the performance order varied for other statistical indicators, overall, the CNN method was the best, while the BP-ANN and RBF-ANN method was the worst among the five examined machine methods. Hence, adopting the CNN approach in this study can enhance LSM accuracy, catering to the needs of planners and government agencies responsible for managing landslide-prone areas and preventing landslide-induced disasters. [ABSTRACT FROM AUTHOR]

Satellite image time series (SITS) is a sequence of satellite images that record a given area at several consecutive times. The aim of such sequences is to use not only spatial information but also the temporal dimension of the data, which is used for multiple real-world applications, such as classification, segmentation, anomaly detection, and prediction. Several traditional machine learning algorithms have been developed and successfully applied to time series for predictions. However, these methods have limitations in some situations, thus deep learning (DL) techniques have been introduced to achieve the best performance. Reviews of machine learning and DL methods for time series prediction problems have been conducted in previous studies. However, to the best of our knowledge, none of these surveys have addressed the specific case of works using DL techniques and satellite images as datasets for predictions. Therefore, this paper concentrates on the DL applications for SITS prediction, giving an overview of the main elements used to design and evaluate the predictive models, namely the architectures, data, optimization functions, and evaluation metrics. The reviewed DL-based models are divided into three categories, namely recurrent neural network-based models, hybrid models, and feed-forward-based models (convolutional neural networks and multi-layer perceptron). The main characteristics of satellite images and the major existing applications in the field of SITS prediction are also presented in this article. These applications include weather forecasting, precipitation nowcasting, spatio-temporal analysis, and missing data reconstruction. Finally, current limitations and proposed workable solutions related to the use of DL for SITS prediction are also highlighted. [ABSTRACT FROM AUTHOR]

The images of the Sentinel-2 constellation can help the verification process of farmers' declarations, providing, among other things, accurate spatial explicit maps of the agricultural land cover. The aim of the study is to design, develop, and evaluate two deep learning (DL) architectures tailored for agricultural land cover and crop type mapping. The focus is on a detailed class scheme encompassing fifteen distinct classes, utilizing Sentinel-2 imagery acquired on a monthly basis throughout the year. The study's geographical scope covers a diverse rural area in North Greece, situated within southeast Europe. These architectures are a Temporal Convolutional Neural Network (CNN) and a combination of a Recurrent and a 2D Convolutional Neural Network (R-CNN), and their accuracy is compared to the well-established Random Forest (RF) machine learning algorithm. The comparative approach is not restricted to simply presenting the results given by classification metrics, but it also assesses the uncertainty of the classification results using an entropy measure and the spatial distribution of the classification errors. Furthermore, the issue of sampling strategy for the extraction of the training set is highlighted, targeting the efficient handling of both the imbalance of the dataset and the spectral variability of instances among classes. The two developed deep learning architectures performed equally well, presenting an overall accuracy of 90.13% (Temporal CNN) and 90.18% (R-CNN), higher than the 86.31% overall accuracy of the RF approach. Finally, the Temporal CNN method presented a lower entropy value (6.63%), compared both to R-CNN (7.76%) and RF (28.94%) methods, indicating that both DL approaches should be considered for developing operational EO processing workflows. [ABSTRACT FROM AUTHOR]

To overcome the interference of noise on the exploration effectiveness of the controlled-source electromagnetic method (CSEM), we improved the deep learning algorithm by combining the denoising convolutional neural network (DnCNN) with the residual network (ResNet), and propose a method based on the residual denoising convolutional neural network (ResDnCNN) and shift-invariant sparse coding (SISC) for denoising CSEM data. Firstly, a sample library was constructed by adding simulated noises of different types and amplitudes to high-quality CSEM data collected. Then, the sample library was used for model training in the ResDnCNN, resulting in a network model specifically designed for denoising CSEM data. Subsequently, the trained model was employed to denoise the measured data, generating preliminary denoised data. Finally, the preliminary denoised data was processed using SISC to obtain the final denoised high-quality data. Comparative experiments with the ResNet, DnCNN, U-Net, and long short-term memory (LSTM) networks demonstrated the significant advantages of our proposed method. It effectively removed strong noise such as Gaussian, impulse, and square wave, resulting in an improvement of the signal-to-noise ratio by nearly 20 dB. Testing on CSEM data from Sichuan Province, China, showed that the apparent resistivity curves plotted using our method were smoother and more credible. [ABSTRACT FROM AUTHOR]

We describe the production of maps of buildings on Hawai'i Island, based on complementary information contained in two different types of remote sensing data. The maps cover 3200 km2 over a highly varied set of landscape types and building densities. A convolutional neural network was first trained to identify building candidates in LiDAR data. To better differentiate between true buildings and false positives, the CNN-based building probability map was then used, together with 400–2400 nm imaging spectroscopy, as input to a gradient boosting model. Simple vector operations were then employed to further refine the final maps. This stepwise approach resulted in detection of 84%, 100%, and 97% of manually labeled buildings, at the 0.25, 0.5, and 0.75 percentiles of true building size, respectively, with very few false positives. The median absolute error in modeled building areas was 15%. This novel integration of deep learning, machine learning, and multi-modal remote sensing data was thus effective in detecting buildings over large scales and diverse landscapes, with potential applications in urban planning, resource management, and disaster response. The adaptable method presented here expands the range of techniques available for object detection in multi-modal remote sensing data and can be tailored to various kinds of input data, landscape types, and mapping goals. [ABSTRACT FROM AUTHOR]

This work proposes an active learning (AL) methodology to create models for the segmentation of fire and smoke in video images. With this model, a model learns in an incremental manner over several AL rounds. Initially, the model is trained in a given subset of samples, and in each AL round, the model selects the most informative samples to be added to the training set in the next training session. Our approach is based on a decomposition of the task in an AL classification phase, followed by an attention-based segmentation phase with class activation mapping on the learned classifiers. The use of AL in classification and segmentation tasks resulted in a 2% improvement in accuracy and mean intersection over union. More importantly, we showed that the approach using AL achieved results similar to non-AL with fewer labeled data samples. [ABSTRACT FROM AUTHOR]

Recently, deep learning has been successfully and widely used in hyperspectral image (HSI) classification. Considering the difficulty of acquiring HSIs, there are usually a small number of pixels used as the training instances. Therefore, it is hard to fully use the advantages of deep learning networks; for example, the very deep layers with a large number of parameters lead to overfitting. This paper proposed a dynamic wide and deep neural network (DWDNN) for HSI classification, which includes multiple efficient wide sliding window and subsampling (EWSWS) networks and can grow dynamically according to the complexity of the problems. The EWSWS network in the DWDNN was designed both in the wide and deep direction with transform kernels as hidden units. These multiple layers of kernels can extract features from the low to high level, and because they are extended in the wide direction, they can learn features more steadily and smoothly. The sliding windows with the stride and subsampling were designed to reduce the dimension of the features for each layer; therefore, the computational load was reduced. Finally, all the weights were only from the fully connected layer, and the iterative least squares method was used to compute them easily. The proposed DWDNN was tested with several HSI data including the Botswana, Pavia University, and Salinas remote sensing datasets with different numbers of instances (from small to big). The experimental results showed that the proposed method had the highest test accuracies compared to both the typical machine learning methods such as support vector machine (SVM), multilayer perceptron (MLP), radial basis function (RBF), and the recently proposed deep learning methods including the 2D convolutional neural network (CNN) and the 3D CNN designed for HSI classification. [ABSTRACT FROM AUTHOR]

Automatic building extraction has been applied in many domains. It is also a challenging problem because of the complex scenes and multiscale. Deep learning algorithms, especially fully convolutional neural networks (FCNs), have shown robust feature extraction ability than traditional remote sensing data processing methods. However, hierarchical features from encoders with a fixed receptive field perform weak ability to obtain global semantic information. Local features in multiscale subregions cannot construct contextual interdependence and correlation, especially for large-scale building areas, which probably causes fragmentary extraction results due to intra-class feature variability. In addition, low-level features have accurate and fine-grained spatial information for tiny building structures but lack refinement and selection, and the semantic gap of across-level features is not conducive to feature fusion. To address the above problems, this paper proposes an FCN framework based on the residual network and provides the training pattern for multi-modal data combining the advantage of high-resolution aerial images and LiDAR data for building extraction. Two novel modules have been proposed for the optimization and integration of multiscale and across-level features. In particular, a multiscale context optimization module is designed to adaptively generate the feature representations for different subregions and effectively aggregate global context. A semantic guided spatial attention mechanism is introduced to refine shallow features and alleviate the semantic gap. Finally, hierarchical features are fused via the feature pyramid network. Compared with other state-of-the-art methods, experimental results demonstrate superior performance with 93.19 IoU, 97.56 OA on WHU datasets and 94.72 IoU, 97.84 OA on the Boston dataset, which shows that the proposed network can improve accuracy and achieve better performance for building extraction. [ABSTRACT FROM AUTHOR]

Identifying permanent water and temporary water in flood disasters efficiently has mainly relied on change detection method from multi-temporal remote sensing imageries, but estimating the water type in flood disaster events from only post-flood remote sensing imageries still remains challenging. Research progress in recent years has demonstrated the excellent potential of multi-source data fusion and deep learning algorithms in improving flood detection, while this field has only been studied initially due to the lack of large-scale labelled remote sensing images of flood events. Here, we present new deep learning algorithms and a multi-source data fusion driven flood inundation mapping approach by leveraging a large-scale publicly available Sen1Flood11 dataset consisting of roughly 4831 labelled Sentinel-1 SAR and Sentinel-2 optical imagery gathered from flood events worldwide in recent years. Specifically, we proposed an automatic segmentation method for surface water, permanent water, and temporary water identification, and all tasks share the same convolutional neural network architecture. We utilize focal loss to deal with the class (water/non-water) imbalance problem. Thorough ablation experiments and analysis confirmed the effectiveness of various proposed designs. In comparison experiments, the method proposed in this paper is superior to other classical models. Our model achieves a mean Intersection over Union (mIoU) of 52.99 % , Intersection over Union (IoU) of 52.30 % , and Overall Accuracy (OA) of 92.81 % on the Sen1Flood11 test set. On the Sen1Flood11 Bolivia test set, our model also achieves very high mIoU ( 47.88 % ), IoU ( 76.74 % ), and OA ( 95.59 % ) and shows good generalization ability. [ABSTRACT FROM AUTHOR]

Wetlands are important ecosystems that are linked to climate change mitigation. As 25% of global wetlands are located in Canada, accurate and up-to-date wetland classification is of high importance, nationally and internationally. The advent of deep learning techniques has revolutionized the current use of machine learning algorithms to classify complex environments, specifically in remote sensing. In this paper, we explore the potential and possible limitations to be overcome regarding the use of ensemble deep learning techniques for complex wetland classification and discusses the potential and limitation of various solo convolutional neural networks (CNNs), including DenseNet, GoogLeNet, ShuffleNet, MobileNet, Xception, Inception-ResNet, ResNet18, and ResNet101 in three different study areas located in Newfoundland and Labrador, Canada (i.e., Avalon, Gros Morne, and Grand Falls). Moreover, to improve the classification accuracies of wetland classes of bog, fen, marsh, swamp, and shallow water, the results of the three best CNNs in each study area is fused using three supervised classifiers of random forest (RF), bagged tree (BTree), Bayesian optimized tree (BOT), and one unsupervised majority voting classifier. The results suggest that the ensemble models, in particular BTree, have a valuable role to play in the classification of wetland classes of bog, fen, marsh, swamp, and shallow water. The ensemble CNNs show an improvement of 9.63–19.04% in terms of mean producer's accuracy compared to the solo CNNs, to recognize wetland classes in three different study areas. This research indicates a promising potential for integrating ensemble-based learning and deep learning for operational large area land cover, particularly complex wetland type classification. [ABSTRACT FROM AUTHOR]

Oat products are significant parts of a healthy diet. Pure oat is gluten-free, which makes it an excellent choice for people with celiac disease. Elimination of alien cereals is important not only in gluten-free oat production but also in seed production. Detecting gluten-rich crops such as wheat, rye, and barley in an oat production field is an important initial processing step in gluten-free food industries; however, this particular step can be extremely time consuming. This article demonstrates the potential of emerging drone techniques for identifying alien barleys in an oat stand. The primary aim of this study was to develop and assess a novel machine-learning approach that automatically detects and localizes barley plants by employing drone images. An Unbiased Teacher v2 semi-supervised object-detection deep convolutional neural network (CNN) was employed to detect barley ears in drone images with a 1.5 mm ground sample distance. The outputs of the object detector were transformed into ground coordinates by employing a photogrammetric technique. The ground coordinates were analyzed with the kernel density estimate (KDE) clustering approach to form a probabilistic map of the ground locations of barley plants. The detector was trained using a dataset from a reference data production site (located in Ilmajoki, Finland) and tested using a 10% independent test data sample from the same site and a completely unseen dataset from a commercial gluten-free oats production field in Seinäjoki, Finland. In the reference data production dataset, 82.9% of the alien barley plants were successfully detected; in the independent farm test dataset, 60.5% of the ground-truth barley plants were correctly recognized. Our results establish the usefulness and importance of the proposed drone-based ultra-high-resolution red–green–blue (RGB) imaging approach for modern grain production industries. [ABSTRACT FROM AUTHOR]

Mesoscale convective systems (MCSs) and associated hazardous meteorological phenomena cause considerable economic damage and even loss of lives in the mid-latitudes. The mechanisms behind the formation and intensification of MCSs are still not well understood due to limited observational data and inaccurate climate models. Improving the prediction and understanding of MCSs is a high-priority area in hydrometeorology. One may study MCSs either employing high-resolution atmospheric modeling or through the analysis of remote sensing images which are known to reflect some of the characteristics of MCSs, including high temperature gradients of cloud-top, specific spatial shapes of temperature patterns, etc. However, research on MCSs using remote sensing data is limited by inadequate (in size) databases of satellite-identified MCSs and poorly equipped automated tools for MCS identification and tracking. In this study, we present (a) the GeoAnnotateAssisted tool for fast and convenient visual identification of MCSs in satellite imagery, which is capable of providing AI-generated suggestions of MCS labels; (b) the Dataset of Mesoscale Convective Systems over the European Territory of Russia (DaMesCoS-ETR), which we created using this tool, and (c) the Deep Convolutional Neural Network for the Identification of Mesoscale Convective Systems (MesCoSNet), constructed following the RetinaNet architecture, which is capable of identifying MCSs in Meteosat MSG/SEVIRI data. We demonstrate that our neural network, optimized in terms of its hyperparameters, provides high MCS identification quality ( mAP = 0.75 , true positive rate TPR = 0.61 ) and a well-specified detection uncertainty (false alarm ratio FAR = 0.36 ). Additionally, we demonstrate potential applications of the GeoAnnotateAssisted labelling tool, the DaMesCoS-ETR dataset, and the MesCoSNet neural network in addressing MCS research challenges. Specifically, we present the climatology of axisymmetric MCSs over the European territory of Russia from 2014 to 2020 during summer seasons (May to September), obtained using MesCoSNet with Meteosat MSG/SEVIRI data. The automated identification of MCSs by the MesCoSNet artificial neural network opens up new avenues for previously unattainable MCS research topics. [ABSTRACT FROM AUTHOR]

Advances in deep learning and computer vision are making significant contributions to flood mapping, particularly when integrated with remotely sensed data. Although existing supervised methods, especially deep convolutional neural networks, have proved to be effective, they require intensive manual labeling of flooded pixels to train a multi-layer deep neural network that learns abstract semantic features of the input data. This research introduces a novel weakly supervised approach for pixel-wise flood mapping by leveraging multi-temporal remote sensing imagery and image processing techniques (e.g., Normalized Difference Water Index and edge detection) to create weakly labeled data. Using these weakly labeled data, a bi-temporal U-Net model is then proposed and trained for flood detection without the need for time-consuming and labor-intensive human annotations. Using floods from Hurricanes Florence and Harvey as case studies, we evaluated the performance of the proposed bi-temporal U-Net model and baseline models, such as decision tree, random forest, gradient boost, and adaptive boosting classifiers. To assess the effectiveness of our approach, we conducted a comprehensive assessment that (1) covered multiple test sites with varying degrees of urbanization, and (2) utilized both bi-temporal (i.e., pre- and post-flood) and uni-temporal (i.e., only post-flood) input. The experimental results showed that the proposed framework of weakly labeled data generation and the bi-temporal U-Net could produce near real-time urban flood maps with consistently high precision, recall, f1 score, IoU score, and overall accuracy compared with baseline machine learning algorithms. [ABSTRACT FROM AUTHOR]

Remote sensing has dramatically increased the available quantity of marine data, and artificial intelligence technologies have demonstrated the ability to process big data and derive meaningful insights from them. Unlike field observation or field sensing, remote sensing is the process of obtaining information about an object or phenomenon without making physical contact. To this end, a two-step convolutional neural network is used to extract cloud transparency information and then generate ground surface information for thin cloud regions. Measured LFMC data, MODIS, Landsat-8, and Sentinel-1 remote sensing data and auxiliary data, such as canopy height and land cover in wildfire-prone areas in the western United States, are selected as study subjects. [Extracted from the article]

The atmospheric temperature profile is an important parameter to describe the state of the atmosphere, and it is crucial to climate change research, weather forecasting, and atmospheric parameter retrieval. A machine learning algorithm that incorporates historical observations and ground-based measurements was developed in this study to retrieve the atmospheric temperature profile. Specifically, the deep learning network considered historical observations for the same period and temporally correlated temperature profiles. It combined multi-layer perceptron (MLP) and the convolutional neural network (CNN). MLP derived the features from the ground factors, and CNN captured the essential features associated with the temperature profiles at the current time from latent historical data. Then, the features of the two parts were concatenated to obtain the final network. The construction and parameters of the model were optimized to determine the best model configuration and retrieval performance. The results of the model were evaluated against those of other methods on the same dataset. The model showed a good retrieval precision, which was equivalent to a small retrieval bias, root-mean-square error, and mean absolute error at all altitudes. The analysis of the application of this model to the retrieval of atmospheric temperature profiles indicates that the method is feasible. [ABSTRACT FROM AUTHOR]

Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km2) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a F 1 -score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ice sheet which further highlights the potential for spatio-temporal transferability. Future work involves the integration of more training data as well as intra-annual analyses of supraglacial lake occurrence across the whole continent and with focus on supraglacial lake development throughout a summer melt season and into Antarctic winter. [ABSTRACT FROM AUTHOR]

Automatic and efficient ground penetrating radar (GPR) data analysis remains a bottleneck, especially restricting applications in real-time monitoring systems. Deep learning approaches have good practice in automatic object identification, but their intensive data requirement has reduced their applicability. This paper developed a machine learning framework based on wavelet scattering networks to analyze GPR data for subsurface pipeline identification. Wavelet scattering network is functionally equivalent to convolutional neural networks, and its null-parameter property is intended for non-intensive datasets. A double-channel framework is designed with wavelet scattering networks followed by support vector machines to determine the existence of pipelines on vertical and horizontal traces separately. Classification accuracy rates arrive around 98% and 95% for datasets without and with noises, respectively, as well as 97% for considering surface roughness. Pipeline locations and diameters are convenient to determine from the reconstructed profiles of both simulated and practical GPR signals. However, the results of 5 cm pipelines are sensitive to noises. Nonetheless, the developed machine learning approach presents promising applicability in subsurface pipeline identification. [ABSTRACT FROM AUTHOR]

Traditional mapping and monitoring of agricultural fields are expensive, laborious, and may contain human errors. Technological advances in platforms and sensors, followed by artificial intelligence (AI) and deep learning (DL) breakthroughs in intelligent data processing, led to improving the remote sensing applications for precision agriculture (PA). Therefore, technological advances in platforms and sensors and intelligent data processing methods, such as machine learning and DL, and geospatial and remote sensing technologies, have improved the quality of agricultural land monitoring for PA needs. However, providing ground truth data for model training is a time-consuming and tedious task and may contain multiple human errors. This paper proposes an automated and fully unsupervised framework based on image processing and DL methods for plant detection in agricultural lands from very high-resolution drone remote sensing imagery. The proposed framework's main idea is to automatically generate an unlimited amount of simulated training data from the input image. This capability is advantageous for DL methods and can solve their biggest drawback, i.e., requiring a considerable amount of training data. This framework's core is based on the faster regional convolutional neural network (R-CNN) with the backbone of ResNet-101 for object detection. The proposed framework's efficiency was evaluated by two different image sets from two cornfields, acquired by an RGB camera mounted on a drone. The results show that the proposed method leads to an average counting accuracy of 90.9%. Furthermore, based on the average Hausdorff distance (AHD), an average object detection localization error of 11 pixels was obtained. Additionally, by evaluating the object detection metrics, the resulting mean precision, recall, and F1 for plant detection were 0.868, 0.849, and 0.855, respectively, which seem to be promising for an unsupervised plant detection method. [ABSTRACT FROM AUTHOR]

Nowadays, different machine learning approaches, either conventional or more advanced, use input from different remote sensing imagery for land cover classification and associated decision making. However, most approaches rely heavily on time-consuming tasks to gather accurate annotation data. Furthermore, downloading and pre-processing remote sensing imagery used to be a difficult and time-consuming task that discouraged policy makers to create and use new land cover maps. We argue that by combining recent improvements in deep learning with the use of powerful cloud computing platforms for EO data processing, specifically the Google Earth Engine, we can greatly facilitate the task of land cover classification. For this reason, we modify an efficient semantic segmentation approach (U-TAE) for a satellite image time series to use, as input, a single multiband image composite corresponding to a specific time range. Our motivation is threefold: (a) to improve land cover classification performance and at the same time reduce complexity by using, as input, satellite image composites with reduced noise created using temporal median instead of the original noisy (due to clouds, calibration errors, etc.) images, (b) to assess performance when using as input different combinations of satellite data, including Sentinel-2, Sentinel-1, spectral indices, and ALOS elevation data, and (c) to exploit channel attention instead of the temporal attention used in the original approach. We show that our proposed modification on U-TAE (mIoU: 57.25%) outperforms three other popular approaches, namely random forest (mIoU: 39.69%), U-Net (mIoU: 55.73%), and SegFormer (mIoU: 53.5%), while also using fewer training parameters. In addition, the evaluation reveals that proper selection of the input band combination is necessary for improved performance. [ABSTRACT FROM AUTHOR]