scholarly journals Neural Network-Based Urban Change Monitoring with Deep-Temporal Multispectral and SAR Remote Sensing Data

2021 ◽  
Vol 13 (15) ◽  
pp. 3000
Author(s):  
Georg Zitzlsberger ◽  
Michal Podhorányi ◽  
Václav Svatoň ◽  
Milan Lazecký ◽  
Jan Martinovič
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Urban Change ◽  
Small Scale ◽  
Atmospheric Effects ◽  
Wide Field ◽  
Ground Truth Data ◽  
Automated Method ◽  
Urban Monitoring ◽  
Sar Data

Remote-sensing-driven urban change detection has been studied in many ways for decades for a wide field of applications, such as understanding socio-economic impacts, identifying new settlements, or analyzing trends of urban sprawl. Such kinds of analyses are usually carried out manually by selecting high-quality samples that binds them to small-scale scenarios, either temporarily limited or with low spatial or temporal resolution. We propose a fully automated method that uses a large amount of available remote sensing observations for a selected period without the need to manually select samples. This enables continuous urban monitoring in a fully automated process. Furthermore, we combine multispectral optical and synthetic aperture radar (SAR) data from two eras as two mission pairs with synthetic labeling to train a neural network for detecting urban changes and activities. As pairs, we consider European Remote Sensing (ERS-1/2) and Landsat 5 Thematic Mapper (TM) for 1991–2011 and Sentinel 1 and 2 for 2017–2021. For every era, we use three different urban sites—Limassol, Rotterdam, and Liège—with at least 500km2 each, and deep observation time series with hundreds and up to over a thousand of samples. These sites were selected to represent different challenges in training a common neural network due to atmospheric effects, different geographies, and observation coverage. We train one model for each of the two eras using synthetic but noisy labels, which are created automatically by combining state-of-the-art methods, without the availability of existing ground truth data. To combine the benefit of both remote sensing types, the network models are ensembles of optical- and SAR-specialized sub-networks. We study the sensitivity of urban and impervious changes and the contribution of optical and SAR data to the overall solution. Our implementation and trained models are available publicly to enable others to utilize fully automated continuous urban monitoring.

Soil salinity assessment using temporal series of Sentinel2 satellite images in irrigated paddy fields of Western Africa

2020 ◽  
Author(s):  
Moussa Issaka ◽  
Walter Christian ◽  
Michot Didier ◽  
Pichelin Pascal ◽  
Nicolas Hervé ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Soil Salinity ◽  
Ground Truth ◽  
Growing Season ◽  
Bare Soil ◽  
Atmospheric Effects ◽  
Ground Truth Data ◽  
Multi Temporal ◽  
Salinity Index ◽  
Niger River

<p>Salinization and alkalinization are worldwide among the soil degradation threats in irrigated schemes affecting soil productivity. Niger River basin irrigated schemes in the Sahel arid zone are no exception (ONAHA, 2011). The use of remote sensing for identifying and evaluating the level of these phenomena is an interesting tool. The launching of the Sentinel2 satellite constellation (2015) brings new perspectives with high spectral and temporal resolutions images. The aim of this study was to develop a methodology for detection of salt-affected soils in this climatic condition.</p><p>To achieve our goal, we used two types of data: remote sensing and ground truth data.</p><p>Two complementary approaches were used: one by observing salinity on bare soil by the use of salinity index (SI) and the other by observing the indirect effects of salinity on the vegetation during eight (8) rice growth phases  using vegetation index NDVI.</p><p>Remote sensing data were acquired from multi temporal sentinel2 images over 4 years (from 11/12/2015 to 30/11/2019). One hundred and fifty seven (157) images were downloaded (one image each 5 days) and corrected from atmospheric effects and some bands resampled to 5 m using python software. The salinity and vegetation indices were calculated. NDVI index was calculated and NDVI integral between NDVI curve and the threshold of 0.21 NDVI calculated for the eight growing cycles.</p><p>Ground truth data were collected in 2019 during the dry growing season (January – may 2019) from 24 calibration plots and 40 validation plots. One hundred and twenty (120) soil samples collected and analyzed for pH and electrical conductivity and finally forty six (46) biomass samples were collected, air dried and weighed for biomass yield and 46 grains samples collected for grain yield.</p><p>NDVI integral proved to be good indicator for yield variations and could distinguish crops behavior according to the growing period. It also makes it possible to distinguish plots which were not cultivated or with weak growth due to strong constraints of which the main one is salinity. It showed also that the effect of salinity on growth differs according to the growing season and the possibility of managing irrigation. Bare soil analysis distinguishes fields with different salinity indexes despite the low number of dates for which bare soil can be observed.</p><p>Ascending Hierarchical Classification (AHC) enabled to identify four classes of NDVI dynamics over time and bare soil salinity index. High saline soils according to direct soil measurements were related to the class characterized by high frequency of no-cultivation during the dry season and low NDVI integral during the wet season. Multi-temporal Sentinel2 images analysis enabled therefore to detect rice crop fields affected by salinity through its influence on crop behavior. This approach will be tested over the whole paddy schemes of the Niger River valley.</p>

scholarly journals Coffee Flower Identification Using Binarization Algorithm Based on Convolutional Neural Network for Digital Images

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Pengliang Wei ◽  
Ting Jiang ◽  
Huaiyue Peng ◽  
Hongwei Jin ◽  
Han Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Digital Images ◽  
Time Lapse ◽  
Identification Accuracy ◽  
Support Vector ◽  
Small Scale ◽  
Binarization Algorithm

Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5° angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.

scholarly journals Intercomparing CO<sub>2</sub> amounts from dispersion modeling, 1.6 μm differential absorption lidar and open path FTIR at a natural CO<sub>2</sub> release at Caldara di Manziana, Italy

2015 ◽  
Vol 8 (4) ◽  
pp. 4325-4345 ◽  
Author(s):  
M. Queißer ◽  
D. Granieri ◽  
M. Burton ◽  
A. La Spina ◽  
G. Salerno ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Dispersion Model ◽  
Central Italy ◽  
Small Scale ◽  
Atmospheric Effects ◽  
Differential Absorption ◽  
Differential Absorption Lidar ◽  
Gas Dispersion ◽  
Open Path ◽  
Co2 Concentrations

Abstract. We intercompare results of three independent approaches to quantify a vented CO2 release at a strongly non-uniform CO2 Earth degassing at Caldara di Manziana, central Italy. An integrated path differential absorption lidar prototype and a commercial open path FTIR system were measuring column averaged CO2 concentrations in parallel at two different paths. An Eulerian gas dispersion model simulated 3-D CO2 concentration maps in the same area, using in situ CO2 flux input data acquired at 152 different points. Local processes the model does not account for, such as small-scale and short-lived wind eddies, govern CO2 concentrations in the instrument measurement paths. The model, on the other hand, also considers atmospheric effects that are out of the field of view of the instruments. Despite this we find satisfactory agreement between modeled and measured CO2 concentrations under certain meteorological conditions. Under these conditions the results suggest that an Eulerian dispersion model and optical remote sensing can be used as an integrated, complementary monitoring approach for CO2 hazard or leakage assessment. Furthermore, the modeling may assist in evaluating CO2 sensing surveys in the future. CO2 column amounts from differential absorption lidar are in line with those from FTIR for both paths with a mean residual of the time series of 44 and 34 ppm, respectively. This experiment is a fundamental step forward in the deployment of the differential absorption lidar prototype as a highly portable active remote sensing instrument probing vented CO2 emissions, including volcanoes.

scholarly journals Multi-Temporal Loess Landslide Inventory Mapping with C-, X- and L-Band SAR Datasets—A Case Study of Heifangtai Loess Landslides, China

2018 ◽  
Vol 10 (11) ◽  
pp. 1756 ◽  
Author(s):  
Xiaojie Liu ◽  
Chaoying Zhao ◽  
Qin Zhang ◽  
Jianbing Peng ◽  
Wu Zhu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Synthetic Aperture Radar ◽  
Landslide Inventory ◽  
Synthetic Aperture ◽  
Small Scale ◽  
Alos Palsar ◽  
Multi Temporal ◽  
Loess Landslides ◽  
L Band ◽  
Sar Data

The Interferometric Synthetic Aperture Radar (InSAR) technique is a well-developed remote sensing tool which has been widely used in the investigation of landslides. Average deformation rates are calculated by weighted averaging (stacking) of the interferograms to detect small-scale loess landslides. Heifangtai loess terrace, Gansu province China, is taken as a test area. Aiming to generate multi-temporal landslide inventory maps and to analyze the landslide evolution features from December 2006 to November 2017, a large number of Synthetic Aperture Radar (SAR) datasets acquired by L-band ascending ALOS/PALSAR, L-band ascending and descending ALOS/PALSAR-2, X-band ascending and descending TerraSAR-X and C-band descending Sentinel-1A/B images covering different evolution stages of Heifangtai terrace are fully exploited. Firstly, the surface deformation of Heifangtai terrace is calculated for independent SAR data using the InSAR technique. Subsequently, InSAR-derived deformation maps, SAR intensity images and a DEM gradient map are jointly used to detect potential loess landslides by setting the appropriate thresholds. More than 40 active loess landslides are identified and mapped. The accuracy of the landslide identification results is verified by comparison with published literatures, the results of geological field surveys and remote sensing images. Furthermore, the spatiotemporal evolution characteristics of the landslides during the last 11 years are revealed for the first time. Finally, strengths and limitations of different wavelength SAR data, and the effects of track direction, geometric distortions of SAR images and the differences in local incidence angle between two adjacent satellite tracks in terms of small-scale loess landslides identification, are analyzed and summarized, and some suggestions are given to guide the future identification of small-scale loess landslides with the InSAR technique.

Small Scale and Low Latency Oriented Neural Network Physical Unclonable Function and its Evaluation

2020 ◽  
Vol 140 (12) ◽  
pp. 1297-1306
Author(s):  
Shu Takemoto ◽  
Kazuya Shibagaki ◽  
Yusuke Nozaki ◽  
Masaya Yoshikawa
Keyword(s):  
Neural Network ◽  
Small Scale ◽  
Low Latency ◽  
Physical Unclonable Function

Random Forest (RF) and Artificial Neural Network (ANN) Algorithms for LULC Mapping

2020 ◽  
Vol 38 (4A) ◽  
pp. 510-514
Author(s):  
Tay H. Shihab ◽  
Amjed N. Al-Hameedawi ◽  
Ammar M. Hamza
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Artificial Neural Network ◽  
Random Forest ◽  
Satellite Image ◽  
Landsat 8 ◽  
Optical Remote Sensing ◽  
Data Set ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this paper to make use of complementary potential in the mapping of LULC spatial data is acquired from LandSat 8 OLI sensor images are taken in 2019.  They have been rectified, enhanced and then classified according to Random forest (RF) and artificial neural network (ANN) methods. Optical remote sensing images have been used to get information on the status of LULC classification, and extraction details. The classification of both satellite image types is used to extract features and to analyse LULC of the study area. The results of the classification showed that the artificial neural network method outperforms the random forest method. The required image processing has been made for Optical Remote Sensing Data to be used in LULC mapping, include the geometric correction, Image Enhancements, The overall accuracy when using the ANN methods 0.91 and the kappa accuracy was found 0.89 for the training data set. While the overall accuracy and the kappa accuracy of the test dataset were found 0.89 and 0.87 respectively.

Small-scale vegetation mapping of large territories: perspectives of using modern remote sensing and GIS technologies, the Indian experiences

1996 ◽  
pp. 51-54 ◽  
Author(s):  
N. V. M. Unni
Keyword(s):  
Remote Sensing ◽  
Satellite Remote Sensing ◽  
Forest Cover ◽  
Human Life ◽  
Remote Sensing Data ◽  
Modern World ◽  
Small Scale ◽  
Vegetation Map ◽  
Gis Technologies ◽  
Forest Cover Mapping

The recognition of versatile importance of vegetation for the human life resulted in the emergence of vegetation science and many its applications in the modern world. Hence a vegetation map should be versatile enough to provide the basis for these applications. Thus, a vegetation map should contain not only information on vegetation types and their derivatives but also the geospheric and climatic background. While the geospheric information could be obtained, mapped and generalized directly using satellite remote sensing, a computerized Geographic Information System can integrate it with meaningful vegetation information classes for large areas. Such aft approach was developed with respect to mapping forest vegetation in India at. 1 : 100 000 (1983) and is in progress now (forest cover mapping at 1 : 250 000). Several review works reporting the experimental and operational use of satellite remote sensing data in India were published in the last years (Unni, 1991, 1992, 1994).

Modeling of the atmospheric effects and its application to the remote sensing of ocean color

1983 ◽  
Vol 22 (23) ◽  
pp. 3751 ◽  
Author(s):  
P. Y. Deschamps ◽  
M. Herman ◽  
D. Tanre
Keyword(s):  
Remote Sensing ◽  
Ocean Color ◽  
Atmospheric Effects

MILL: Channel Attention–based Deep Multiple Instance Learning for Landslide Recognition

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-11
Author(s):  
Xiaochuan Tang ◽  
Mingzhe Liu ◽  
Hao Zhong ◽  
Yuanzhen Ju ◽  
Weile Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Large Scale ◽  
Remote Sensing Image ◽  
Disaster Risk ◽  
Multiple Instance Learning ◽  
Remote Sensing Images ◽  
Loess Area ◽  
Remote Sensing Image Classification ◽  
Natural Disaster Risk

Landslide recognition is widely used in natural disaster risk management. Traditional landslide recognition is mainly conducted by geologists, which is accurate but inefficient. This article introduces multiple instance learning (MIL) to perform automatic landslide recognition. An end-to-end deep convolutional neural network is proposed, referred to as Multiple Instance Learning–based Landslide classification (MILL). First, MILL uses a large-scale remote sensing image classification dataset to build pre-train networks for landslide feature extraction. Second, MILL extracts instances and assign instance labels without pixel-level annotations. Third, MILL uses a new channel attention–based MIL pooling function to map instance-level labels to bag-level label. We apply MIL to detect landslides in a loess area. Experimental results demonstrate that MILL is effective in identifying landslides in remote sensing images.

Sign in / Sign up

Export Citation Format

Share Document