Manual Visual Interpretation Research Articles

Incremental learning model for sustainable agricultural land assessment using multimodal satellite data

ABSTRACT The identification of agricultural lands is crucial for sustainable development in rural areas. In this paper, an augmented model that utilizes multimodal satellite-based data samples for identifying agricultural lands via incremental learning. The Whale Optimization Algorithm (WOA) is used for augmenting collected images and data samples to enhance the accuracy of the model under real-time conditions. To identify agricultural lands, Deep Convolutional Neural Networks (CNNs) are trained on the augmented data samples. Additionally, the incorporation of Q-Learning for continuous optimization of the model to enhance its efficiency and effectiveness in identifying agricultural lands. The proposed model offers many edges over existing methods. Firstly, the use of multimodal satellite-based data samples allows for a comprehensive and accurate analysis of agricultural lands. Secondly, the incorporation of the Whale Optimization Algorithm enables the augmentation of collected data samples, leading to improved accuracy and reliability of the model. Thirdly, Deep CNNs allows the extraction of complex features from the data, leading to more accurate identification of agricultural lands. Finally, the use of Q-Learning ensures that the model is continuously optimized to improve its efficiency and effectiveness. The need for this work arises from the limitations of existing methods in accurately identifying agricultural lands. Traditional methods based on manual surveys and visual interpretation are time-consuming, expensive, and prone to errors. Moreover, existing automated methods often lack the ability to analyse multimodal satellite-based data samples and fail to provide accurate results. Based on these observations, the proposed augmented model offers a promising solution for identifying agricultural lands for sustainable development. The use of multimodal satellite-based data samples, WOA, Deep CNNs, and Q-Learning allows for an accurate and efficient analysis of agricultural lands, which can aid in sustainable development planning and decision-making operations.

False alarm suppressing for passive underwater acoustic target detecting with computer visual techniques

Given the complexity of marine environments, the detection of underwater acoustic targets frequently relies on manual visual interpretation of the imagery displayed on monitoring screens, which limits the application of related technologies on unmanned platforms. To replace human visual observation, understanding, and reasoning within underwater unmanned equipment, this study explores an intelligent detection method for Bearing Time Records based on computer vision techniques, drawing inspiration from human visual perception in detecting targets on BTR images. Firstly, an unsupervised learning method is employed to extract the bases representing various signal patterns from BTR images, with clear physical meanings. Subsequently, we utilize both algorithm-driven and data-driven methods for automated base classification, and both methods achieve a remarkable 100% accuracy rate in automatic base classification. In comparison to human visual detection, this automated approach exhibits a false alarm rate of less than 3%.

Detecting Lunar Linear Structures Based on Multimodal Semantic Segmentation: The Case of Sinuous Rilles

Tectonic features on the Moon can reflect the state of stress during the formation of the structure, and sinuous rilles can provide further insight into the tectonic-thermal evolution of the Moon. Manual visual interpretation is the primary method for extracting these linear structures due to their complex morphology. However, extracting these features from the vast amount of lunar remote sensing data requires significant time and effort from researchers, especially for small-scale tectonic features, such as wrinkle ridges, lobate scarps, and high-relief ridges. In order to enhance the efficiency of linear structure detection, this paper conducts research on the automatic detection method of linear structures using sinuous rilles as an example case. In this paper, a multimodal semantic segmentation method, “Sinuous Rille Network (SR-Net)”, for detecting sinuous rilles is proposed based on DeepLabv3+. This method combines advanced techniques such as ECA-ResNet and dynamic feature fusion. Compared to other networks, such as PSPNet, ResUNet, and DeepLabv3+, SR-Net demonstrates superior precision (95.20%) and recall (92.18%) on the multimodal sinuous rille test set. The trained SR-Net was applied in detecting lunar sinuous rilles within the range of 60°S to 60°N latitude. A new catalogue of sinuous rilles was generated based on the results of the detection process. The methodology proposed in this paper is not confined to the detection of sinuous rilles; with further improvements, it can be extended to the detection of other linear structures.

The first hillslope thermokarst inventory for the permafrost region of the Qilian Mountains

Abstract. Climate warming and anthropogenic disturbances result in permafrost degradation in cold regions, including in the Qilian Mountains. These changes lead to extensive hillslope thermokarst (HT) formation, such as retrogressive thaw slumps, active-layer detachment slides, and thermal erosion gullies. These in turn cause, e.g., degradation of local vegetation, economic losses, infrastructure damages, and threats to human safety. However, despite its importance, there is currently no thermokarst inventory for the Qilian Mountains. Through manual visual interpretation and field validation, we therefore produce the first quantification of HT features. We count a total of 1064 HT features, with 67 % located in the upper reaches of the Heihe River basin, which encompasses ∼ 13 % of the Qilian Mountains region. We further identified that 187 HT features (18 %) existed before 2010, while the remaining 874 (82 %) were initiated in the recent period. More specifically, 392 sites (37 %) were initiated during 2010–2015 and 482 (45 %) after 2015. Thermokarst terrain is observed primarily in areas with shallow active-layer depths (average thickness 2.98 m) on northern shaded slopes of 3–25°, with low solar radiation and moderate elevations ranging from 3200 to 4000 m. This first inventory of HT features is an important and missing piece in documenting changes on the Qinghai–Tibetan Plateau, and this new dataset also provides an important basis for further studies, such as automated extraction of HT features, susceptibility analysis of HT, and estimation of losses caused by HT. The datasets are available from the National Tibetan Plateau/Third Pole Environment Data Center and can be downloaded from https://doi.org/10.11888/Cryos.tpdc.300805 (Peng and Yang, 2023).

Open-Pit Granite Mining Area Extraction Using UAV Aerial Images and the Novel GIPNet

The ability to rapidly and accurately delineate open-pit granite mining areas is pivotal for effective production planning and environmental impact assessment. Over the years, advancements in remote sensing techniques, including the utilization of satellite imagery, LiDAR technology and unmanned aerial vehicles, have revolutionized the way mining areas are monitored and managed. Simultaneously, in the context of the open-pit mining area extraction task, deep learning-based automatic recognition is gradually replacing manual visual interpretation. Leveraging the potential of unmanned aerial vehicles (UAVs) for real-time, low-risk remote sensing, this study employs UAV-derived orthophotos for mining area extraction. Central to the proposed approach is the novel Gather–Injection–Perception (GIP) module, designed to overcome the information loss typically associated with conventional feature pyramid modules during feature fusion. The GIP module effectively enriches semantic features, addressing a crucial information limitation in existing methodologies. Furthermore, the network introduces the Boundary Perception (BP) module, uniquely tailored to tackle the challenges of blurred boundaries and imprecise localization in mining areas. This module capitalizes on attention mechanisms to accentuate critical high-frequency boundary details in the feature map and synergistically utilizes both high- and low-dimensional feature map data for deep supervised learning. The suggested method demonstrates its superiority in a series of comparative experiments on a specially assembled dataset of research area images. The results are compelling, with the proposed approach achieving 90.67% precision, 92.00% recall, 91.33% F1-score, and 84.04% IoU. These figures not only underscore the effectiveness of suggested model in enhancing the extraction of open-pit granite mining areas but also provides a new idea for the subsequent application of UAV data in the mining scene.

Assessment of rock glaciers and their water storage in Guokalariju, Tibetan Plateau

Abstract. Rock glaciers are important hydrological reserves in arid and semi-arid regions. Their activity states can indicate the existence of permafrost. To help further explore the development mechanisms of rock glaciers in semi-arid and humid transition regions, this paper provides a detailed rock glacier inventory of the Guokalariju (also known as Goikarla Rigyu) area of the Tibetan Plateau (TP) using a manual visual interpretation of Google Earth Pro remote sensing imagery. We also estimated the water volume equivalent (WVEQ) in the study area for the first time. Approximately 5057 rock glaciers were identified, covering a total area of ∼404.69 km2. Rock glaciers are unevenly distributed within the three sub-regions from west to east, with 80 % of them concentrated in the central region, where climatic and topographic conditions are most favorable. Under the same ground temperature conditions, increases in precipitation are conducive to rock glaciers forming at lower altitudes. Indeed, the lower limit of rock glaciers' mean altitude decreased eastward with increasing precipitation. Estimates of the water storage capacity of rock glaciers obtained by applying different methods varied considerably, but all showed the potential hydrological value of rock glaciers. The possible water storage in the subsurface ice of rock glacier permafrost was 1.32–3.60 km3. The ratio between the amount of subsurface ice stored in rock glaciers and surface ice stored in local glaciers falls within the range of 1:2.32 to 1:1.26, with an average ratio of 1:1.69. In the west region, where the climate is the driest, the water storage capacity of rock glaciers was estimated to be up to twice as large as that of the sub-region's glaciers. Changes in water resources and permafrost stability in the area where rock glaciers occur will have implications for regional water resource management, disaster prevention, and sustainable development strategies.

Study on diel migration of zooplankton in the Arctic surrounding seas during summer season based on mathematical statistics

Marine zooplankton have diel vertical migration behavior and play a key role in the transport of surface organic compounds to the deep ocean, which is of great significance in studying marine climate change. In this research, the manual visual interpretation method was used to preprocess the biological backscattering intensity data of acoustic Doppler current profiler (ADCP) during the eighth Arctic expedition. Results showed that the extracted vertical migration trajectory was in good agreement with the variation of backscattering intensity data. The amount of zooplankton in the Arctic Ocean is significantly lower than that in the North Pacific and the North Atlantic, and sea ice cover has a significant effect on the diel vertical migration of zooplankton. Characteristics of zooplankton distribution in the North Atlantic Ocean were analyzed based on mathematical statistical methods. The results also prove that the backscattering intensity of -90dB can distinguish scattering layer and water, and that of -78dB can distinguish general scatters and zooplankton. There are two significant concentrations of zooplankton in the Atlantic Ocean which were located at the surface and at depths of 350-450 m, respectively.

Application of optimized CNN algorithm in landslide boundary detection

Landslide, as a natural geological phenomenon with great harm, seriously threatens human social activities and life safety. It has a variety of latent and immeasurable destructiveness, which has a significant impact on the economic losses in rural areas. Therefore, it is urgent to take measures to accurately identify landslides to reduce their negative impacts. However, traditional manual visual interpretation has been unable to meet the current needs for emergency rescue of landslides, so computer intelligent methods have been paid attention to. This study proposes a new recognition network to address the problem of low accuracy of intelligent landslide boundary recognition methods. Firstly, the experiment incorporated boundary structure information into the Full Convolutional Network (FCN) for optimization, and constructed an Improved Full Convolutional Network (IFCN) model to better achieve image reconstruction. After that, Attention Mechanism (AM) is further introduced to achieve accurate detection of landslide boundaries in images, namely the IFCN-AM model. The attention mechanism introduced include spatial attention mechanism and multi-channel attention mechanism. Both are responsible for enhancing the language representation ability of the model and aggregating the interrelated features between different channels. The experimental results show that IFCN-AM has a 3 % to 7 % improvement in accuracy, recall, F1 value, and MIoU value.

Mountain Forest Type Classification Based on One-Dimensional Convolutional Neural Network

Convolutional neural networks (CNNs) have demonstrated their efficacy in remote sensing applications for mountain forest classification. However, two-dimensional convolutional neural networks (2D CNNs) require a significant manual involvement in the visual interpretation to obtain continuous polygon label data. To reduce the errors associated with manual visual interpretation and enhance classification efficiency, it is imperative to explore alternative approaches. In this research, we introduce a novel one-dimensional convolutional neural network (1D CNN) methodology that directly leverages field investigation data as labels for classifying mountain forest types based on multiple remote sensing data sources. The hyperparameters were optimised using an orthogonal table, and the model’s performance was evaluated on Mount Emei of Sichuan Province. Comparative assessments with traditional classification methods, namely, a random forest (RF) and a support vector machine (SVM), revealed superior results obtained by the proposed 1D CNN. Forest type classification using the 1D CNN achieved an impressive overall accuracy (OA) of 97.41% and a kappa coefficient (Kappa) of 0.9673, outperforming the U-Net (OA: 94.45%, Kappa: 0.9239), RF (OA: 88.99%, Kappa: 0.8488), and SVM (OA: 88.79%, Kappa: 0.8476). Moreover, the 1D CNN model was retrained using limited field investigation data from Mount Wawu in Sichuan Province and successfully classified forest types in that region, thereby demonstrating its spatial-scale transferability with an OA of 90.86% and a Kappa of 0.8879. These findings underscore the effectiveness of the proposed 1D CNN in utilising multiple remote sensing data sources for accurate mountain forest type classification. In summary, the introduced 1D CNN presents a novel, efficient, and reliable method for mountain forest type classification, offering substantial contributions to the field.

SE-YOLOv7 Landslide Detection Algorithm Based on Attention Mechanism and Improved Loss Function

With the continuous development of computer vision technology, more and more landslide identification detection tasks have started to shift from manual visual interpretation to automatic computer identification, and automatic landslide detection methods based on remote sensing satellite images and deep learning have been gradually developed. However, most existing algorithms often have the problem of low precision and weak generalization in landslide detection. Based on the Google Earth Engine platform, this study selected landslide image data from 24 study areas in China and established the DN landslide sample dataset, which contains a total of 1440 landslide samples. The original YOLOv7 algorithm model was improved and optimized by applying the SE squeezed attention mechanism and VariFocal loss function to construct the SE-YOLOv7 model to realize the automatic detection of landslides in remote sensing images. The experimental results show that the mAP, Precision value, Recall value, and F1-Score of the improved SE-YOLOv7 model for landslide identification are 91.15%, 93.35%, 94.54%, and 93.94%, respectively. At the same time, through a field investigation and verification study in Qianyang County, Baoji City, Shaanxi Province, comparing the detection results of SE-YOLOv7, it is concluded that the improved SE-YOLOv7 can locate the landslide location more accurately, detect the landslide range more accurately, and have fewer missed detections. The research results show that the algorithm model has strong detection accuracy for many types of landslide image data, which provides a technical reference for future research on landslide detection based on remote sensing images.

Automated Detection of Central-positive Complexes & Postictal Generalized EEG Suppression in ECT-induced Seizures – An Illustrative Case Report (P10-1.009)

<h3>Objective:</h3> We present a case of using automated algorithms to analyze central-positive complexes (CPCs) and postictal generalized electroencephalographic suppression (PGES) in the context of ECT-induced seizures. Our goal is to characterize peri-ictal EEG changes in ECT-induced seizures to define their unique features as generalized seizures. <h3>Background:</h3> Generalized seizures induced by electroconvulsive therapy (ECT) have been proposed as a model to study epileptic seizures in humans. We recently described generalized, high-amplitude waveforms with maximum positive voltage over the vertex (CPCs) during ECT-induced seizures. Furthermore, we developed an automated algorithm for detecting postictal PGES, defined as electroencephalographic (EEG) activity of ≤10 mV following a generalized seizure. <h3>Design/Methods:</h3> This investigation is a secondary analysis of data collected from Reconstructing Consciousness and Cognition Phase 2 study (ClinicalTrials.gov NCT02761330). A 53-year-old female with a diagnosis of major depressive disorder underwent 5 sessions of right unilateral ECT during concurrent 64-channel EEG recordings. Quantitative EEG analysis allowed for assessment of spatiotemporal properties and spectral content during the peri-ictal period. CPC and PGES durations, quantified by automated algorithms, were compared to those derived through visual interpretation by expert epileptologists. <h3>Results:</h3> CPCs occurred during Phase III of all recorded seizures, with a median duration of 41 seconds. CPC evolved from 4.1 to 3.2 Hz as the seizures progressed. Peak-amplitude CPC scalp topology was consistent across patient’s seizures, showing maximal positive polarity over the vertex and surrounding regions and maximal negative polarity over the subocular electrodes. PGES duration lasted 5–45 seconds (median of 22 seconds) following the seizure and the median time to responsiveness after the seizure was 18.3 minutes. The findings using the automated algorithm were comparable to manual visual interpretation. <h3>Conclusions:</h3> This case presents the utility of automated algorithms to analyze CPCs and PGES characteristics, many of which were comparable to those evaluated through visual EEG interpretation. <b>Disclosure:</b> Dr. Nayak has nothing to disclose. Dr. Kafashan has nothing to disclose. Dr. Nascimento has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Zogenix. The institution of Dr. Nascimento has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Biocodex. Dr. Nascimento has received personal compensation in the range of $500-$4,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for AAN. The institution of Dr. Nascimento has received research support from Zogenix. The institution of Dr. Nascimento has received research support from Biocodex. The institution of Dr. Nascimento has received research support from Greenwich. Dr. Nascimento has received publishing royalties from a publication relating to health care. Dr. Nascimento has a non-compensated relationship as a Editorial Team Member with Neurology RFS that is relevant to AAN interests or activities. Dr. Nascimento has a non-compensated relationship as a Production Team with Neurology Podcast that is relevant to AAN interests or activities. The institution of Dr. Palanca has received research support from National Institutes of Health. The institution of Dr. Palanca has received research support from McDonnell Center for Systems Neuroscience. The institution of Dr. Palanca has received research support from American Federation for Suicide Prevention. Dr. Palanca has received intellectual property interests from a discovery or technology relating to health care. Dr. Palanca has received personal compensation in the range of $100,000-$499,999 for serving as a Employee with Washington University School of Medicine in St. Louis. Dr. Hogan has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Neurelis. The institution of Dr. Hogan has received research support from Biogen Inc. The institution of Dr. Hogan has received research support from Engage Therapeutics. The institution of Dr. Hogan has received research support from Otsuka Pharmaceuticals. The institution of Dr. Hogan has received research support from Cerevel Therapeutics.

Earthquake-induced building damage recognition from unmanned aerial vehicle remote sensing using scale-invariant feature transform characteristics and support vector machine classification

Building damage is the main cause of casualties and economic losses from earthquakes. Therefore, understanding building damage is critical for emergency handling. Current information acquisition methods for assessing earthquake damage using unmanned aerial vehicle (UAV) remote sensing systems offer great flexibility and high efficiency with the capability to obtain high-resolution images, which can reflect actual damage to affected areas intuitively. Consequently, UAV remote sensing has become a convenient and important means to acquire earthquake-induced building damage information. Although manual visual interpretation can achieve high recognition accuracy, it is extremely time-consuming. In contrast, although current automatic recognition methods require less time, they have relatively poor recognition accuracy. Neither approach can satisfactorily simultaneously meet efficiency and accuracy requirements for earthquake emergency handling. This article applies image classification algorithms based on the support vector machine (SVM) to earthquake-induced building damage recognition, and proposes a recognition method based on scale-invariant feature transform (SIFT) characteristics and SVM classification. We use the magnitude 6.4 earthquake at Yangbi (2021) as an example to validate the proposed method. Results verify that the proposed method can recognize earthquake damage quickly and accurately, providing effective support for decision-making regarding rescue actions.

Glacier Retreating Analysis on the Southeastern Tibetan Plateau via Multisource Remote Sensing Data

Accurate multitemporal glacier change investigations and analyses are lacking on the southeastern Tibetan Plateau (SETP). A combination of photogrammetry, optical remote sensing and synthetic aperture radar (SAR) datasets can accurately identify large-scale glaciers; In the present study, glaciers in three periods on the SETP (1970s, 2000, 2020) were identified from multisource remote sensing data based on a deep learning method and manual visual interpretation, and multitemporal glacial inventory data from relatively high-frequency source imagery. Totals of 11648, 12993, and 11875 glaciers were identified in the 1970s, 2000, and 2020, with total areas of 13372.08 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , 11692.31 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , and 10612.94 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , respectively. The general distribution of SETP glaciers was identified to be typical of alpine glaciers dominated by small-sized glaciers. The average elevation of glaciers was approximately 5000 m; the slopes were mostly lower than 40°, and the main aspect was southeast, followed by south and southwest. The glaciers retreated from the 1970s to 2020, and a total glacier area of approximately 2759.14 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> was degraded during this time, with an average annual melting rate of 0.45% yr <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-1</sup> . Rising summer temperatures may be the driving force behind the continuous decline in the glacier area. Overall, the results obtained in this study showed relatively low uncertainty involved in the identification of glaciers compared to some previous studies. The results can provide accurate glacier information for glacier monitoring and modeling studies on the SETP.

Review for Region Localization in Large-Scale Optical Remote Sensing Images

For the massive large-scale visible image data obtained by satellite, unmanned aerial vehicles, and other reconnaissance platforms, if only relying on manual visual interpretation, there will be problems such as heavy workload, low efficiency, high repeatability, strong subjectivity, and high cost, which cannot meet the demand of modern society for efficient information. Therefore, in order to improve work efficiency, it is necessary to study the rapid automatic region localization in large-scale remote sensing images. That will play an important role in change detection, temperature retrieval, and other files. The development and present situation of the region localization algorithms are analyzed. This paper summarizes the development, improvement, and deficiency of the traditional algorithm, as well as the difficulties and challenges. And the authors make a comparison to the deep learning-based methods. Finally, a possible development direction is prospected.

ICESat-2 laser data denoising algorithm based on a back propagation neural network.

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) photon data is the emerging satellite-based LiDAR data, widely used in surveying and mapping due to its small photometric spot and high density. Since ICESat-2 data collect weak signals, it is difficult to denoise in shallow sea island areas, and the quality of the denoising method will directly affect the precision of bathymetry. This paper proposes a back propagation (BP) neural network-based denoising algorithm for the data characteristics of shallow island reef areas. First, a horizontal elliptical search area is constructed for the photons in the dataset. Suitable feature values are selected in the search area to train the BP neural network. Finally, data with a geographic location far apart, including daily and nightly data, are selected respectively for experiments to test the generality of the network. By comparing the results with the confidence labels provided in the official documents of the ATL03 dataset, the DBSCAN algorithm, and the manual visual interpretation, it is proved that the denoising algorithm proposed in this paper has a better processing effect in shallow island areas.

Patagonian Andes Landslides Inventory: The Deep Learning’s Way to Their Automatic Detection

Landslide inventories are crucial to studying the dynamics, associated risks, and effects of these geomorphological processes on the evolution of mountainous landscapes. The production of landslide maps is mainly based on manual visual interpretation methods of aerial and satellite images combined with field surveys. In recent times, advances in machine learning methods have made it possible to explore new semi-automated landslide detection methodologies using remotely detected images. In this sense, developing new artificial intelligence models based on Deep Learning (DL) opens up an excellent opportunity to automate this arduous process. Although the Andes mountain range is one of the most geomorphologically active areas on the planet, the few investigations that use DL mainly focus on mountain ranges in Europe and Asia. One of the main reasons is the low density of landslide data available in the Andean areas, making it difficult to experiment with DL models requiring large data volumes. In this work, we seek to narrow the existing gap in the availability of landslide inventories in the area of the Patagonian Andes. In addition, the feasibility and efficiency of DL techniques are studied to develop landslide detection models in the Andes from the generated datasets. To achieve this goal, we generated in a manual process a datasets of 10,000 landslides for northern Chilean Patagonia (42–45°S), being the largest freely accessible landslide datasets in this region. We implement a machine learning model, through DL, to detect landslides in optical images of the Sentinel-2 constellation using a model based on the DeepLabv3+ architecture, a state-of-the-art deep learning network for semantic segmentation. Our results indicate that the algorithm detects landslides with an accuracy of 0.75 at the object level. For its part, the segmentation reaches a precision of 0.86, a recall of 0.74, and an F1-score of 0.79. The correlation of the segmentation measured through the Matthews correlation coefficient shows a value of 0.59, and the geometric similarity of the correctly detected landslides measured through the Jaccard score reaches 0.70. Although the model shows a good response in the testing area, errors are generated that can be explained by geometric and spectral relationships, which should be solved through new training approaches and data sets.

Analysis of Landscape Pattern Evolution and Driving Forces Based on Land-Use Changes: A Case Study of Yilong Lake Watershed on Yunnan-Guizhou Plateau

In order to explore the landscape pattern evolution and driving forces of the Yilong Lake watershed, the combined method of supervised classification with manual visual interpretation based on the landsat5TM/8OLI remote sensing image data sources was used to establish a high-precision spatial distribution information database of the Yilong Lake watershed. Landscape index was used to analyze the distribution and spatial pattern change characteristics of various land-use types. Based on correlation and principal component analysis, we discuss the relationship between the change characteristics of land-use type, distribution and spatial pattern, and the interference of local socio-economic development and natural factors. The results show that: (1) In the past 30 years, the land-use types of the Yilong Lake watershed are mainly forest, garden plot and cultivated land. The forest area decreased significantly by 30.45 km2, of which the fastest reduction stage was from 2000 to 2005, with a total reduction of 20.56 km2. The garden plot conversion is relatively large, with a total of 181.69 km2 transferred out, of which 28.84 km2 has become unused land, respectively. (2) In the past 30 years, the maximum patch index decreased by 9.94% and the patch density index increased by 14.25%, indicating that the landscape fragmentation in the whole basin increased. The Shannon diversity index showed an increasing process; the aggregation index showed a decreasing process. (3) The change in landscape pattern in the watershedwas closely related to economic growth, population growth, social affluence and agricultural development. Natural factors, social factors and economic indicators are significantly positively correlated with patch density, edge density, landscape shape index and Shannon diversity index, and significantly negatively correlated with the largest patch index and the contagion index. On the whole, the wetlands in the basin are shrinking and the landscape diversity is changing. Reducing the excessive impact of human activities on the watershed ecosystem is a key factor for the local protection of wetland resources and the maintenance of wetland ecological functions.

Application of Deep Learning in Land Use Classification for Soil Erosion Using Remote Sensing

China is suffering from serious soil and water loss due to improper land use, leading to flood and drought disasters, and industrial and agricultural reduction. The commonly used monitoring methods of soil and water loss rely on the visual interpretation of remote sensing images, which is time-consuming and laborious. In this study, deep learning semantic segmentation technology was applied to monitoring land use for soil and water conservation. Manual visual interpretation mark samples and land use products collected in recent years were combined to construct training samples for deep learning. Deep convolution neural network model based on ResNet152 and DeeplabV3+ was selected for performing land use classification. Then the soil and water loss were quantified using the Chinese Soil Loss Equation (CSLE) based on the hydrological, geographic, vegetation cover and land use information. The experimental results show that the deep learning model can quickly extract robust edge features from remote sensing images and has high pixel accuracy (83.4%). Although the model accuracy was affected by the land cover types and image quality in different study area, it can still achieve an accuracy higher than 70% in other counties through our experiment. It can further improve the information service level of soil and water conservation product, and provide a useful guideline for automatic land use interpretation and identification of soil and water conservation status based on high resolution remote sensing images.

Geological Remote Sensing Interpretation Using Deep Learning Feature and an Adaptive Multisource Data Fusion Network

Geological remote sensing interpretation can extract elements of interest from multiple types of images, which is vital in geological survey and mapping, especially in inaccessible regions. However, due to numerous classes, high interclass similarities, complex distributions, and sample imbalances of geological elements, the interpretation results of machine-learning (ML)-based methods are understandably worse than manual visual interpretation. Additionally, scholars in remote sensing have mainly carried out their works to interpret a single geological element category, such as mineral, lithological, soil and structure. The interpretation of multiple geological elements is missing, which is more in line with the open world. To improve the interpretation results of ML-based methods and reduce the labor cost in geological survey and mapping, we propose a deep-learning (DL)-feature-based adaptive multi-source data fusion network (AMSDFNet) for the efficient interpretation of multiple geological remote sensing elements. The AMSDFNet has two branches for learning valuable spatial and spectral information from two kinds of data sources, wherein the atrous spatial pyramid pooling operation and an attention block are applied to adaptively extract and fuse multi-scale informative features. A hard example mining algorithm was also added to select important training examples to address sample imbalance. A large-scale region in western China with sufficient geological elements was set as the research area. The proposed model improved the two critical metrics by more than 2% in the experiment section. As far as we know, this research work is the first time DL features and multi-source remote sensing images have been utilized to simultaneously interpret geological elements of lithology, soil, surface water, and glaciers. The extensive experimental results demonstrated the superiority of DL features and our model in geological remote sensing interpretation.

Development and distribution of ancient landslides in the northwest corner of the Tibetan Plateau

The periphery of the Tibetan Plateau is a landslide-prone area, yet there is a lack of satisfactory results on the development and distribution of landslides due to low human activity and inconvenient transportation within this area. In this study, taking 38–40°N and 73–76°E as the study region, a detailed distribution map of ancient landslides, including 5378 landslides with a total area of 2705.02 km2, is established with the help of Google Earth Engine platform using manual visual interpretation. The numbers and areas of landslides, classified in terms of elevation, slope angle, slope aspect, fault distance, and water system distance, are analyzed. The development of landslides is closely correlated with topographical and geological factors. After comprehensive analysis, we conclude that both the number and total area of landslides in the elevation range of 4–5 km are the greatest; more landslides happen in the slope angle range of 40°–50°; the total area of landslides in the slope angle range of 50°–60° is the largest; both the number and total area of landslides with slope aspects of N, NE, and NW are the greatest; the ancient landslides in this region were weakly impacted by tectonic movement and seismic activity, and more likely caused by reasons like climate change; and the occurrence of ancient landslides in this region is insignificantly correlated with water systems.