Preliminary verification for application of a support vector machine based cloud detection method to GOSAT-2 CAI-2

Abstract. The Greenhouse Gases Observing Satellite (GOSAT) was launched in 2009 to measure global atmospheric CO2 and CH4 concentrations. GOSAT is equipped with two sensors: the thermal and near-infrared sensor for carbon observation (TANSO)-Fourier transform spectrometer (FTS) and TANSO-cloud and aerosol imager (CAI). The presence of clouds in the instantaneous field of view of the FTS leads to incorrect estimates of the concentrations. Thus, the FTS data suspected to have cloud contamination must be identified by a CAI cloud discrimination algorithm and rejected. Conversely, overestimating clouds reduces the amount of FTS data that can be used to estimate greenhouse gases concentrations. This is a serious problem in tropical rainforest regions, such as the Amazon, where the amount of useable FTS data is small because of cloud cover. Preparations are continuing for the launch of the GOSAT-2 in fiscal year 2018. To improve the accuracy of the estimates of greenhouse gases concentrations, we need to refine the existing CAI cloud discrimination algorithm: Cloud and Aerosol Unbiased Decision Intellectual Algorithm (CLAUDIA1). A new cloud discrimination algorithm using a support vector machine (CLAUDIA3) was developed and presented in another paper. Visual inspection can use the locally optimized standards for judging, although CLAUDIA1 and CLAUDIA3 use common thresholds all over the world. Thus, the accuracy of visual inspection is better than that of these algorithms in most regions, with the exception of snow and ice covered surfaces, where there is not enough spectral contrast to distinguish cloud. For the reason visual inspection can be used for the truth metric for the verification exercise. In this study, we compared between CLAUDIA1-CAI and CLAUDIA3-CAI for various land cover types, and evaluated the accuracy of CLAUDIA3-CAI by comparing the both of CLAUDIA1-CAI and CLAUDIA3-CAI against visual inspection of the same CAI images in tropical rainforests. Comparative results between CLAUDIA1-CAI and CLAUDIA3-CAI for various land cover types indicated that CLAUDIA3-CAI had tendency to identify bright surface and optically thin clouds, however, misjudge the edges of clouds as compared with CLAUDIA1-CAI. The accuracy of CLAUDIA3-CAI was approximately 89.5 % in tropical rainforests, which is greater than that of CLAUDIA1-CAI (85.9 %) for the test cases presented here.

Download Full-text

Preliminary verification for application of a support vector machine-based cloud detection method to GOSAT-2 CAI-2

Atmospheric Measurement Techniques ◽

10.5194/amt-11-2863-2018 ◽

2018 ◽

Vol 11 (5) ◽

pp. 2863-2878 ◽

Cited By ~ 3

Author(s):

Yu Oishi ◽

Haruma Ishida ◽

Takashi Y. Nakajima ◽

Ryosuke Nakamura ◽

Tsuneo Matsunaga

Keyword(s):

Support Vector Machine ◽

Land Cover ◽

Greenhouse Gases ◽

Visual Inspection ◽

Fiscal Year ◽

Tropical Rainforests ◽

Support Vector ◽

Accuracy Evaluation ◽

Data Set ◽

Land Cover Types

Abstract. The Greenhouse Gases Observing Satellite (GOSAT) was launched in 2009 to measure global atmospheric CO2 and CH4 concentrations. GOSAT is equipped with two sensors: the Thermal And Near infrared Sensor for carbon Observations (TANSO)-Fourier transform spectrometer (FTS) and TANSO-Cloud and Aerosol Imager (CAI). The presence of clouds in the instantaneous field of view of the FTS leads to incorrect estimates of the concentrations. Thus, the FTS data suspected to have cloud contamination must be identified by a CAI cloud discrimination algorithm and rejected. Conversely, overestimating clouds reduces the amount of FTS data that can be used to estimate greenhouse gas concentrations. This is a serious problem in tropical rainforest regions, such as the Amazon, where the amount of useable FTS data is small because of cloud cover. Preparations are continuing for the launch of the GOSAT-2 in fiscal year 2018. To improve the accuracy of the estimates of greenhouse gases concentrations, we need to refine the existing CAI cloud discrimination algorithm: Cloud and Aerosol Unbiased Decision Intellectual Algorithm (CLAUDIA1). A new cloud discrimination algorithm using a support vector machine (CLAUDIA3) was developed and presented in another paper. Although the use of visual inspection of clouds as a standard for judging is not practical for screening a full satellite data set, it has the advantage of allowing for locally optimized thresholds, while CLAUDIA1 and -3 use common global thresholds. Thus, the accuracy of visual inspection is better than that of these algorithms in most regions, with the exception of snow- and ice-covered surfaces, where there is not enough spectral contrast to identify cloud. In other words, visual inspection results can be used as truth data for accuracy evaluation of CLAUDIA1 and -3. For this reason visual inspection can be used for the truth metric for the cloud discrimination verification exercise. In this study, we compared CLAUDIA1–CAI and CLAUDIA3–CAI for various land cover types, and evaluated the accuracy of CLAUDIA3–CAI by comparing both CLAUDIA1–CAI and CLAUDIA3–CAI with visual inspection (400  ×  400 pixels) of the same CAI images in tropical rainforests. Comparative results between CLAUDIA1–CAI and CLAUDIA3–CAI for various land cover types indicated that CLAUDIA3–CAI had a tendency to identify bright surface and optically thin clouds. However, CLAUDIA3–CAI had a tendency to misjudge the edges of clouds compared with CLAUDIA1–CAI. The accuracy of CLAUDIA3–CAI was approximately 89.5 % in tropical rainforests, which is greater than that of CLAUDIA1–CAI (85.9 %) for the test cases presented here.

Download Full-text

An Accurate Vegetation and Non-Vegetation Differentiation Approach Based on Land Cover Classification

Remote Sensing ◽

10.3390/rs12233880 ◽

2020 ◽

Vol 12 (23) ◽

pp. 3880

Author(s):

Chiman Kwan ◽

David Gribben ◽

Bulent Ayhan ◽

Jiang Li ◽

Sergio Bernabe ◽

...

Keyword(s):

Land Cover ◽

Vegetation Index ◽

Near Infrared ◽

Normalized Difference Vegetation Index ◽

Land Cover Classification ◽

Support Vector ◽

Growth Monitoring ◽

Land Cover Types ◽

Imaging Detection ◽

Better Than

Accurate vegetation detection is important for many applications, such as crop yield estimation, land cover land use monitoring, urban growth monitoring, drought monitoring, etc. Popular conventional approaches to vegetation detection incorporate the normalized difference vegetation index (NDVI), which uses the red and near infrared (NIR) bands, and enhanced vegetation index (EVI), which uses red, NIR, and the blue bands. Although NDVI and EVI are efficient, their accuracies still have room for further improvement. In this paper, we propose a new approach to vegetation detection based on land cover classification. That is, we first perform an accurate classification of 15 or more land cover types. The land covers such as grass, shrub, and trees are then grouped into vegetation and other land cover types such as roads, buildings, etc. are grouped into non-vegetation. Similar to NDVI and EVI, only RGB and NIR bands are needed in our proposed approach. If Laser imaging, Detection, and Ranging (LiDAR) data are available, our approach can also incorporate LiDAR in the detection process. Results using a well-known dataset demonstrated that the proposed approach is feasible and achieves more accurate vegetation detection than both NDVI and EVI. In particular, a Support Vector Machine (SVM) approach performed 6% better than NDVI and 50% better than EVI in terms of overall accuracy (OA).

Download Full-text

CLOUD DETECTION OF OPTICAL SATELLITE IMAGES USING SUPPORT VECTOR MACHINE

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xli-b7-289-2016 ◽

2016 ◽

Vol XLI-B7 ◽

pp. 289-293 ◽

Cited By ~ 1

Author(s):

Kuan-Yi Lee ◽

Chao-Hung Lin

Keyword(s):

Support Vector Machine ◽

Land Cover ◽

Satellite Images ◽

Main Idea ◽

Support Vector ◽

Detection Accuracy ◽

Optical Remote Sensing ◽

Cloud Detection ◽

Local Study ◽

Temporal Variance

Cloud covers are generally present in optical remote-sensing images, which limit the usage of acquired images and increase the difficulty of data analysis, such as image compositing, correction of atmosphere effects, calculations of vegetation induces, land cover classification, and land cover change detection. In previous studies, thresholding is a common and useful method in cloud detection. However, a selected threshold is usually suitable for certain cases or local study areas, and it may be failed in other cases. In other words, thresholding-based methods are data-sensitive. Besides, there are many exceptions to control, and the environment is changed dynamically. Using the same threshold value on various data is not effective. In this study, a threshold-free method based on Support Vector Machine (SVM) is proposed, which can avoid the abovementioned problems. A statistical model is adopted to detect clouds instead of a subjective thresholding-based method, which is the main idea of this study. <br><br> The features used in a classifier is the key to a successful classification. As a result, Automatic Cloud Cover Assessment (ACCA) algorithm, which is based on physical characteristics of clouds, is used to distinguish the clouds and other objects. In the same way, the algorithm called Fmask (Zhu et al., 2012) uses a lot of thresholds and criteria to screen clouds, cloud shadows, and snow. Therefore, the algorithm of feature extraction is based on the ACCA algorithm and Fmask. Spatial and temporal information are also important for satellite images. Consequently, co-occurrence matrix and temporal variance with uniformity of the major principal axis are used in proposed method. We aim to classify images into three groups: cloud, non-cloud and the others. In experiments, images acquired by the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and images containing the landscapes of agriculture, snow area, and island are tested. Experiment results demonstrate the detection accuracy of the proposed method is better than related methods.

Download Full-text

CLOUD DETECTION OF OPTICAL SATELLITE IMAGES USING SUPPORT VECTOR MACHINE

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xli-b7-289-2016 ◽

2016 ◽

Vol XLI-B7 ◽

pp. 289-293

Author(s):

Kuan-Yi Lee ◽

Chao-Hung Lin

Keyword(s):

Support Vector Machine ◽

Land Cover ◽

Satellite Images ◽

Main Idea ◽

Support Vector ◽

Detection Accuracy ◽

Optical Remote Sensing ◽

Cloud Detection ◽

Local Study ◽

Temporal Variance

Download Full-text

A comparison of pixel-based decision tree and object-based Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data

International Journal of Remote Sensing ◽

10.1080/01431161.2017.1371864 ◽

2017 ◽

Vol 38 (23) ◽

pp. 7176-7195 ◽

Cited By ~ 12

Author(s):

Qiong Wu ◽

Ruofei Zhong ◽

Wenji Zhao ◽

Han Fu ◽

Kai Song

Keyword(s):

Support Vector Machine ◽

Land Cover ◽

Decision Tree ◽

Land Cover Classification ◽

Airborne Lidar ◽

Aerial Images ◽

Support Vector ◽

Lidar Data ◽

Object Based ◽

Airborne Lidar Data

Download Full-text

A Comparative Study of Support Vector Machine and Maximum Likelihood Classification to Extract Land Cover of Lahore District, Punjab, Pakistan

Pakistan Journal of Scientific & Industrial Research Series A: Physical Sciences ◽

10.52763/pjsir.phys.sci.64.3.2021.265.274 ◽

2021 ◽

Vol 64 (3) ◽

pp. 265-274

Author(s):

Fatima Mushtaq ◽

Khalid Mahmood ◽

Mohammad Chaudhry Hamid ◽

Rahat Tufail

Keyword(s):

Support Vector Machine ◽

Maximum Likelihood ◽

Land Cover ◽

Support Vector ◽

Kappa Statistics ◽

Error Matrix ◽

Classification Techniques ◽

Machine Learning Classification ◽

Hyper Plane ◽

Better Than

The advent of technological era, the scientists and researchers develop machine learning classification techniques to classify land cover accurately. Researches prove that these classification techniques perform better than previous traditional techniques. In this research main objective is to identify suitable land cover classification method to extract land cover information of Lahore district. Two supervised classification techniques i.e., Maximum Likelihood Classifier (MLC) (based on neighbourhood function) and Support Vector Machine (SVM) (based on optimal hyper-plane function) are compared by using Sentinel-2 data. For this optimization, four land cover classes have been selected. Field based training samples have been collected and prepared through a survey of the study area at four spatial levels. Accuracy for each of the classifier has been assessed using error matrix and kappa statistics. Results show that SVM performs better than MLC. Overall accuracies of SVM and MLC are 95.20% and 88.80% whereas their kappa co-efficient are 0.93 and 0.84 respectively.

Download Full-text