Article
Remote Sensing
Saurabh Kaushik, Tejpal Singh, P. K. Joshi, Andreas J. Dietz
Summary: In this study, a fully automated approach for glacial lake mapping using a Deep Convolutional Neural Network (DCNN) and multisource remote sensing data was proposed. Training and testing in the Himalayan region showed that the proposed method outperformed existing techniques and demonstrated transferability and accuracy in different locations.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Environmental Sciences
Daeyong Jin, Eojin Lee, Kyonghwan Kwon, Taeyun Kim
Summary: In this study, convolutional neural networks (CNNs) were used to estimate the spatial and temporal distribution of chlorophyll-a in a bay. By utilizing deep learning models, particularly CNN Model II, the predictive accuracy was improved, with CDOM identified as the most influential variable in estimating chlorophyll-a distribution.
Article
Chemistry, Analytical
Marjorie Darrah, Matthew Richardson, Bradley DeRoos, Mitchell Wathen
Summary: This paper discusses the importance of using high-resolution data for accurate object classification in 3D LiDAR data. The results show that training neural networks with higher resolution data can achieve classification accuracy above 97%, while lower resolution data leads to a drop in accuracy.
Review
Computer Science, Information Systems
Rachana Gupta, Satyasai Jagannath Nanda
Summary: This article introduces a review of various methods for cloud detection and their related applications. The empirical results based on Neural Network (NN) approach are provided for published works from 1970 to 2020. The analysis on multi-spectral satellite images demonstrates the improved performance of NN approach for cloud detection. The article also discusses the algorithm using convolutional neural network (CNN) to enhance the accuracy of cloud detection.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Environmental Sciences
Wanrou Qin, Yan Song, Haitian Zhu, Xinli Yu, Yuhong Tu
Summary: This article utilizes satellite remote sensing data for dynamic monitoring of shipyard production state and proposes an improved evidence fusion method to solve the conflict of evidence, thereby improving monitoring accuracy.
Article
Meteorology & Atmospheric Sciences
Masoud Ghahremanloo, Yannic Lops, Yunsoo Choi, Seyedali Mousavinezhad, Jia Jung
Summary: The study proposes a two-step deep learning model to estimate surface NO2 concentrations using satellite data. The model uses a partial convolutional neural network (PCNN) to impute gaps between surface NO2 stations and then a deep neural network (DNN) to estimate surface NO2 levels. The model achieves exceptional performance and provides gap-free estimates of NO2 grids.
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
(2023)
Article
Engineering, Aerospace
Hong Jiang, Qing He, Jie Zhang, Ye Tang, Chunyan Chen, Xinsheng Lv, Yunhui Zhang, Zonghui Liu
Summary: Accurate identification of dust storm weather is crucial for forecasting and early warning of dust storm disasters. This study proposes a dust storm mask algorithm based on a deep learning convolutional neural network and a physical algorithm to effectively monitor large-scale dust storms.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Engineering, Electrical & Electronic
Luxiao Cheng, Lizhe Wang, Ruyi Feng, Jining Yan
Summary: This study proposes a multimodel fusion neural network that combines a convolutional neural network and a multilayer perceptron model to estimate fine-resolution population distributions from multisource data. Experimental results show that the model accurately captures the relationship between estimated and census populations, as well as identifies population density differences in densely populated areas and remote clusters better than other models.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Seyd Teymoor Seydi, Heidar Rastiveis, Bahareh Kalantar, Alfian Abdul Halin, Naonori Ueda
Summary: In this study, a novel End-to-End convolutional neural network (BDD-Net) is proposed for building damage detection by fusing optical and Lidar datasets. The results show that fusing the data significantly improves the accuracy of building damage map generation, with an overall accuracy greater than 88%.
Article
Geography, Physical
Bruno Adriano, Naoto Yokoya, Junshi Xia, Hiroyuki Miura, Wen Liu, Masashi Matsuoka, Shunichi Koshimura
Summary: Earth observation technologies, such as optical imaging and synthetic aperture radar, play a crucial role in monitoring urban environments, especially in rapid disaster response. Utilizing a global multimodal dataset, a damage mapping framework was developed and deep learning network effectively predicted damaged buildings across various data modality scenarios.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Agriculture, Multidisciplinary
Usman Rauf, Waqar S. Qureshi, Hamid Jabbar, Ayesha Zeb, Alina Mirza, Eisa Alanazi, Umar S. Khan, Nasir Rashid
Summary: In the agriculture sector of Pakistan, a new framework utilizing data from the Sentinal-2 satellite is proposed for accurate mapping and classification of two major rice varieties. The approach collected data from 12 rice fields at 16 time instances and achieved a high overall accuracy.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Remote Sensing
Oliverio J. Santana, Daniel Hernandez-Sosa, Ryan N. Smith
Summary: This study utilizes a convolutional neural network to detect eddies in satellite altimetry maps. The design is relatively simple but performs competitively compared to previous deep learning methods. Additionally, the model is less sensitive to temporal variations and can identify eddies that traditional models may miss.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Engineering, Electrical & Electronic
Weisheng Li, Chao Yang, Yidong Peng, Jiao Du
Summary: This article proposes a pseudo-Siamese deep convolutional neural network (PDCNN) for spatiotemporal fusion, aiming to address the limitations of existing algorithms in spatial detail preservation and spectral change reconstruction. The method introduces a pseudo-Siamese network framework model and technologies such as multiscale mechanism and dilated convolution to improve the accuracy of image reconstruction.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Bin Yang, Le Qin, Jianqiang Liu, Xinxin Liu
Summary: This letter proposes a novel method called IRCNN for change detection in satellite time series. IRCNN is based on deep learning and incorporates convolutional neural networks and irregular-time-distanced recurrent neural networks. Experimental results show that IRCNN outperforms other methods in both qualitative and quantitative aspects.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Review
Ecology
Jinna Lv, Qi Shen, Mingzheng Lv, Yiran Li, Lei Shi, Peiying Zhang
Summary: Semantic segmentation is a challenging task in pixel-level remote sensing data analysis. Deep learning methods have been successfully applied and improved in this field, leading to excellent results. However, there is still a deficiency in the evaluation and advancement of semantic segmentation techniques for remote sensing data. This paper surveys more than 100 papers in the past 5 years and comprehensively summarizes the advantages and disadvantages of techniques and models based on important and difficult points, providing valuable insights for beginners in this field.
FRONTIERS IN ECOLOGY AND EVOLUTION
(2023)