scholarly journals Efficient multi-scale Gaussian process regression for massive remote sensing data with satGP v0.1

2019 ◽  
Author(s):  
Jouni Susiluoto ◽  
Alessio Spantini ◽  
Heikki Haario ◽  
Youssef Marzouk
Keyword(s):  
Remote Sensing ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Remote Sensing Data ◽  
Marginal Maximum Likelihood ◽  
Computationally Efficient ◽  
Covariance Kernel ◽  
Multi Scale ◽  
Covariance Functions ◽  
Sensing Applications

Abstract. Satellite remote sensing provides a global view to processes on Earth that has unique benefits compared to measurements made on the ground. The global coverage and the enormous amounts of data produced come, however, with the price of spatial and temporal gaps and less than perfect data quality. Meaningful statistical inference from such data requires overcoming these problems and that calls for developing efficient computational tools. We design and implement a computationally efficient multi-scale Gaussian process (GP) software package, satGP, geared towards remote sensing applications. The software is designed to be able to handle problems of enormous sizes and is able to compute marginals and sample from a random process with at least over hundred million observations. The mean function of the Gaussian process is described by approximating marginals of a Markov random field (MRF). For covariance functions, Matern, exponential, and periodic kernels are utilized in a multi-scale kernel setting to describe the spatial heterogeneity present in data. We further demonstrate how winds can be used to inform the covariance kernel formulation. The covariance kernel parameters are learned by calculating an approximate marginal maximum likelihood estimate and this is utilized to verify the validity of the multi-scale approach in synthetic experiments. For demonstrating the techniques above, data from the Orbiting Carbon Observatory 2 (OCO-2) satellite is used. The satGP program is released as open source software.

scholarly journals Efficient multi-scale Gaussian process regression for massive remote sensing data with satGP v0.1.2

2020 ◽  
Vol 13 (7) ◽  
pp. 3439-3463
Author(s):  
Jouni Susiluoto ◽  
Alessio Spantini ◽  
Heikki Haario ◽  
Teemu Härkönen ◽  
Youssef Marzouk
Keyword(s):  
Remote Sensing ◽  
Random Field ◽  
Gaussian Process ◽  
Data Set ◽  
Covariance Kernel ◽  
Multi Scale ◽  
Sensing Applications ◽  
The Mean ◽  
Periodic Components ◽  
Kernel Parameters

Abstract. Satellite remote sensing provides a global view to processes on Earth that has unique benefits compared to making measurements on the ground, such as global coverage and enormous data volume. The typical downsides are spatial and temporal gaps and potentially low data quality. Meaningful statistical inference from such data requires overcoming these problems and developing efficient and robust computational tools. We design and implement a computationally efficient multi-scale Gaussian process (GP) software package, satGP, geared towards remote sensing applications. The software is able to handle problems of enormous sizes and to compute marginals and sample from the random field conditioning on at least hundreds of millions of observations. This is achieved by optimizing the computation by, e.g., randomization and splitting the problem into parallel local subproblems which aggressively discard uninformative data. We describe the mean function of the Gaussian process by approximating marginals of a Markov random field (MRF). Variability around the mean is modeled with a multi-scale covariance kernel, which consists of Matérn, exponential, and periodic components. We also demonstrate how winds can be used to inform covariances locally. The covariance kernel parameters are learned by calculating an approximate marginal maximum likelihood estimate, and the validity of both the multi-scale approach and the method used to learn the kernel parameters is verified in synthetic experiments. We apply these techniques to a moderate size ozone data set produced by an atmospheric chemistry model and to the very large number of observations retrieved from the Orbiting Carbon Observatory 2 (OCO-2) satellite. The satGP software is released under an open-source license.

scholarly journals A Spatio-Temporal Local Association Query Algorithm for Multi-Source Remote Sensing Big Data

2021 ◽  
Vol 13 (12) ◽  
pp. 2333
Author(s):  
Lilu Zhu ◽  
Xiaolu Su ◽  
Yanfeng Hu ◽  
Xianqing Tai ◽  
Kun Fu
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Temporal Correlation ◽  
Local Association ◽  
Sensing Data ◽  
Multi Scale ◽  
Correlation Networks ◽  
Efficient Integration ◽  
Spatio Temporal ◽  
Query Algorithm

It is extremely important to extract valuable information and achieve efficient integration of remote sensing data. The multi-source and heterogeneous nature of remote sensing data leads to the increasing complexity of these relationships, and means that the processing mode based on data ontology cannot meet requirements any more. On the other hand, the multi-dimensional features of remote sensing data bring more difficulties in data query and analysis, especially for datasets with a lot of noise. Therefore, data quality has become the bottleneck of data value discovery, and a single batch query is not enough to support the optimal combination of global data resources. In this paper, we propose a spatio-temporal local association query algorithm for remote sensing data (STLAQ). Firstly, we design a spatio-temporal data model and a bottom-up spatio-temporal correlation network. Then, we use the method of partition-based clustering and the method of spectral clustering to measure the correlation between spatio-temporal correlation networks. Finally, we construct a spatio-temporal index to provide joint query capabilities. We carry out local association query efficiency experiments to verify the feasibility of STLAQ on multi-scale datasets. The results show that the STLAQ weakens the barriers between remote sensing data, and improves their application value effectively.

scholarly journals Detecting Forest Degradation in the Three-North Forest Shelterbelt in China from Multi-Scale Satellite Images

2021 ◽  
Vol 13 (6) ◽  
pp. 1131
Author(s):  
Tao Yu ◽  
Pengju Liu ◽  
Qiang Zhang ◽  
Yi Ren ◽  
Jingning Yao
Keyword(s):  
Remote Sensing ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Net Primary Production ◽  
Remote Sensing Data ◽  
Forest Degradation ◽  
Observation Data ◽  
Area Index ◽  
Sensing Data ◽  
Multi Scale

Detecting forest degradation from satellite observation data is of great significance in revealing the process of decreasing forest quality and giving a better understanding of regional or global carbon emissions and their feedbacks with climate changes. In this paper, a quick and applicable approach was developed for monitoring forest degradation in the Three-North Forest Shelterbelt in China from multi-scale remote sensing data. Firstly, Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Ratio Vegetation Index (RVI), Leaf Area Index (LAI), Fraction of Photosynthetically Active Radiation (FPAR) and Net Primary Production (NPP) from remote sensing data were selected as the indicators to describe forest degradation. Then multi-scale forest degradation maps were obtained by adopting a new classification method using time series MODerate Resolution Imaging Spectroradiometer (MODIS) and Landsat Enhanced Thematic Mapper Plus (ETM+) images, and were validated with ground survey data. At last, the criteria and indicators for monitoring forest degradation from remote sensing data were discussed, and the uncertainly of the method was analyzed. Results of this paper indicated that multi-scale remote sensing data have great potential in detecting regional forest degradation.

scholarly journals Measurement of nitrogen content in rice by inversion of hyperspectral reflectance data from an unmanned aerial vehicle

2018 ◽  
Vol 48 (6) ◽  
Author(s):  
Du Wen ◽  
Xu Tongyu ◽  
Yu Fenghua ◽  
Chen Chunling
Keyword(s):  
Remote Sensing ◽  
Nitrogen Content ◽  
Unmanned Aerial Vehicle ◽  
Gaussian Process Regression ◽  
Remote Sensing Data ◽  
Principal Component ◽  
Ground Truth ◽  
Hyperspectral Remote Sensing ◽  
Inversion Algorithm ◽  
Aerial Vehicle

ABSTRACT: The Nitrogen content of rice leaves has a significant effect on growth quality and crop yield. We proposed and demonstrated a non-invasive method for the quantitative inversion of rice nitrogen content based on hyperspectral remote sensing data collected by an unmanned aerial vehicle (UAV). Rice canopy albedo images were acquired by a hyperspectral imager onboard an M600-UAV platform. The radiation calibration method was then used to process these data and the reflectance of canopy leaves was acquired. Experimental validation was conducted using the rice field of Shenyang Agricultural University, which was classified into 4 fertilizer levels: zero nitrogen, low nitrogen, normal nitrogen, and high nitrogen. Gaussian process regression (GPR) was then used to train the inversion algorithm to identify specific spectral bands with the highest contribution. This led to a reduction in noise and a higher inversion accuracy. Principal component analysis (PCA) was also used for dimensionality reduction, thereby reducing redundant information and significantly increasing efficiency. A comparison with ground truth measurements demonstrated that the proposed technique was successful in establishing a nitrogen inversion model, the accuracy of which was quantified using a linear fit (R2=0.8525) and the root mean square error (RMSE=0.9507). These results support the use of GPR and provide a theoretical basis for the inversion of rice nitrogen by UAV hyperspectral remote sensing.

scholarly journals Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery

Water ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 178
Author(s):  
Ali Jamali ◽  
Masoud Mahdianpari
Keyword(s):  
Remote Sensing ◽  
Language Processing ◽  
Coastal Wetland ◽  
Remote Sensing Data ◽  
Machine Learning Algorithms ◽  
Coastal Marsh ◽  
Forested Wetland ◽  
Wetland Classification ◽  
Sensing Applications

The emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, particularly in the classification of wetlands. State-of-the-art Natural Language Processing (NLP) algorithms, on the other hand, are transformers. Despite the fact that transformers have been utilized for a few remote sensing applications, they have not been compared to other well-known CNN networks in complex wetland classification. As such, for the classification of complex coastal wetlands in the study area of Saint John city, located in New Brunswick, Canada, we modified and employed the Swin Transformer algorithm. Moreover, the developed transformer classifier results were compared with two well-known deep CNNs of AlexNet and VGG-16. In terms of average accuracy, the proposed Swin Transformer algorithm outperformed the AlexNet and VGG-16 techniques by 14.3% and 44.28%, respectively. The proposed Swin Transformer classifier obtained F-1 scores of 0.65, 0.71, 0.73, 0.78, 0.82, 0.84, and 0.84 for the recognition of coastal marsh, shrub, bog, fen, aquatic bed, forested wetland, and freshwater marsh, respectively. The results achieved in this study suggest the high capability of transformers over very deep CNN networks for the classification of complex landscapes in remote sensing.

Spatio-temporal Cokriging method for assimilating and downscaling multi-scale remote sensing data

2020 ◽  
pp. 112190
Author(s):  
Bo Yang ◽  
Hongxing Liu ◽  
Emily L. Kang ◽  
Song Shu ◽  
Min Xu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Sensing Data ◽  
Multi Scale ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document