No description available.

No description available.

This study looks at the changes to NDVI value in the Weeks Bay Reserve following the impact by Hurricane Katrina. Four Landsat images from March 24, 2005 (Pre-Katrina), September 16, 2005/ April 26, 2006 (Post-Katrina) and August 7, 2002 (Control) were classified into different landcover types and run with the NDVI vegetation index. Those images were compared against each other and showed that the September image had a NDVI value drop of 49% and the April image had a 47% drop as compared to the previous March. The emergent vegetation surrounding the shoreline was most susceptible to changes in NDVI value and recovered the slowest of the tested landcover types. Swift tracks, bay areas, and rivers in the study area where tested and showed that the rivers are the most susceptible change in NDVI value and recovered the slowest.

Deep-Learning (DL) methods have been widely used for Remote Sensing (RS) applications in the last few years, and they allow improving the analysis of the temporal information in bi-temporal and multi-temporal RS images. DL methods use RS data to classify geographical areas or find changes occurring over time. DL methods exploit multi-sensor or multi-temporal data to retrieve results more accurately than single-source or single-date processing. However, the State-of-the-Art DL methods exploit the heterogeneous information provided by these data by focusing the analysis either on the spatial information of multi-sensor multi-resolution images using multi-scale approaches or on the time component of the image time series. Most of the DL RS methods are supervised, so they require a large number of labeled data that is challenging to gather. Nowadays, we have access to many unlabeled RS data, so the creation of long image time series is feasible. However, supervised methods require labeled data that are expensive to gather over image time series. Hence multi-temporal RS methods usually follow unsupervised approaches. In this thesis, we propose DL methodologies that handle these open issues. We propose unsupervised DL methods that exploit multi-resolution deep feature maps derived by a Convolutional Autoencoder (CAE). These DL models automatically learn spatial features from the input during the training phase without any labeled data. We then exploit the high temporal resolution of image time series with the high spatial information of Very-High-Resolution (VHR) images to perform a multi-temporal and multi-scale analysis of the scene. We merge the information provided by the geometrical details of VHR images with the temporal information of the image time series to improve the RS application tasks. We tested the proposed methods to detect changes over bi-temporal RS images acquired by various sensors, such as Landsat-5, Landsat-8, and Sentinel-2, representing burned and deforested areas, and kinds of pasture impurities using VHR orthophotos and Sentinel-2 image time series. The results proved the effectiveness of the proposed methods.

Self-supervised learning models, which are called foundation models, have achieved great success in computer vision. Meanwhile, the limited access to labeled data has driven the development of self-supervised methods in remote sensing tasks. In remote sensing image change detection, the generative models are extensively utilized in unsupervised binary change detection tasks, while they overly focus on pixels rather than on abstract feature representations. In addition, the state-of-the-art satellite image time series change detection approaches fail to effectively leverage the spatial-temporal information of image time series or generalize well to unseen scenarios. Similarly, in the context of multimodal remote sensing data fusion, the recent successes of deep learning techniques mainly focus on specific tasks and complete data fusion paradigms. These task-specific models lack of generalizability to other remote sensing tasks and become overfitted to the dominant modalities. Moreover, they fail to handle incomplete modalities inputs and experience severe degradation in downstream tasks. To address these challenges associated with individual supervised learning models, this thesis presents two novel contributions to self-supervised learning models on remote sensing image change detection and multimodal remote sensing data fusion. The first contribution proposes a bi-temporal / multi-temporal contrastive change detection framework, which employs contrastive loss on image patches or superpixels to get fine-grained change maps and incorporates an uncertainty method to enhance the temporal robustness. In the context of satellite image time series change detection, the proposed approach improves the consistency of pseudo labels through feature tracking and tackles the challenges posed by seasonal changes in long-term remote sensing image time series using supervised contrastive loss and the random walk loss in ConvLSTM. The second contribution develops a self-supervised multimodal RS data fusion framework, with a specific focus on addressing the incomplete multimodal RS data fusion challenges in downstream tasks. Within this framework, multimodal RS data are fused by applying a multi-view contrastive loss at the pixel level and reconstructing each modality using others in a generative way based on MultiMAE. In downstream tasks, the proposed approach leverages a random modality combination training strategy and an attention block to enable fusion across modal-incomplete inputs. The thesis assesses the effectiveness of the proposed self-supervised change detection approach on single-sensor and cross-sensor datasets of SAR and multispectral images, and evaluates the proposed self-supervised multimodal RS data fusion approach on the multimodal RS dataset with SAR, multispectral images, DEM and also LULC maps. The self-supervised change detection approach demonstrates improvements over state-of-the-art unsupervised change detection methods in challenging scenarios involving multi-temporal and multi-sensor RS image change detection. Similarly, the self-supervised multimodal remote sensing data fusion approach achieves the best performance by employing an intermediate fusion strategy on SAR and optical image pairs, outperforming existing unsupervised data fusion approaches. Notably, in incomplete multimodal fusion tasks, the proposed method exhibits impressive performance on all modal-incomplete and single modality inputs, surpassing the performance of vanilla MultiViT, which tends to overfit on dominant modality inputs and fails in tasks with single modality inputs.

The main objective of this study was to determine the spectral change technique best suited to detect complete forest harvests (clearcuts) in the Southern United States. In the pursuit of this objective eight existing change detection techniques were quantitatively evaluated and a hybrid method was also developed. Secondary objectives were to determine the impact of atmospheric corrections applied before the change detection, and the affect post-processing methods to eliminate small groups of misclassified pixels ("salt and pepper" effect) had on accuracy. Landsat TM imagery of Louisa County, Virginia was acquired on anniversary dates in both 1996 and 1998 (Path 16, Row 34), clipped to the study area boundary, and registered to one another. Previous to the change detection exercise, two levels of atmospheric corrections were applied to the imagery separately to produce three data sets. The three data sets were evaluated to determine what level of pre-processing is necessary for harvest change detection. In addition, eight change detection techniques were evaluated: 1) the 345 TM band differencing, 2) 35 TM band differencing, 3) NDVI differencing, 4) principal component 1 differencing, 5) selection of a change band in a multitemporal PCA, 6) tasseled cap brightness differencing, 7) tasseled cap greenness differencing, and 8) univariate differencing using TM band 7. A hybrid method that used the results from the eight previous techniques was developed. After performing the change detection, majority filters using window sizes of 3x3 pixels, 5x5 pixels, and 7x7 pixels were applied to the change maps to determine how eliminating small groups of misclassified pixels would affect accuracies. Accuracy assessments of the binary (harvested or not harvested) change maps were used to evaluate the accuracies of the various methods described using 256 validation points collected by the Virginia Department of Forestry. The atmospheric corrections did not seem to significantly benefit the change detection techniques, and in some cases actually degraded accuracies. Of the eight techniques applied to the original dataset, univariate differencing using TM band 7 performed the best with a 90.63% overall accuracy, while Tasseled Cap Greenness returned the worst result with an overall accuracy of 78.91%. Principal component 1 differencing and 35 differencing also performed well. The hybrid approach returned good results, but at its best returned an overall accuracy of 90.63%, matching the TM band 7 method. The majority filters using the 3x3 and 5x5 window sizes increased the accuracy in many cases, while the majority filter using the 7x7 window size degraded overall accuracy. / Master of Science

京都大学 / 0048 / 新制・課程博士 / 博士(工学) / 甲第18556号 / 工博第3917号 / 新制||工||1602(附属図書館) / 31456 / 京都大学大学院工学研究科社会基盤工学専攻 / (主査)教授 田村 正行, 准教授 須﨑 純一, 教授 小池 克明 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

No description available.

Karst rocky desertification (KRD) is one kind of severe environmental problem existing in southwest of China. Reveal KRD condition is vital to solve the problem. A way to address the problem is by identifying KRD areas, so that policy-makers and researchers may get a better view of the issue and know where the areas affected by the problem are located. The study area is called Puding which is a county located in the central part of Guizhou province. Based on Landsat data, by using GIS and RS techniques, KRD information of Puding was extracted. Furthermore, the study monitored decades of change of the environmental problem in Puding and predicted possible condition in the future. Other researchers and decision makers may get a better view of the issue from the study results. In addition to Landsat data, other used data includes: ASTER Global digital elevation model data, Modis data, Google Earth data and other thematic maps. In the study, expert classification system and spectral features based model two methods were applied to extract KRD information and compare with each other. Their classified rules were taken from previous studies separately. Necessary preprocessing procedures such as atmospheric correction and geometrical correction were performed before extraction. After extraction relevant results were evaluated and analyzed. Predictions were made by cellular automata Markov module. Based on extracted KRD results, the distribution, percentage, change, and prediction of KRD conditions in Puding were presented. The results of the accuracy evaluation showed that the spectral features based model had acceptable performance. However, the KRD results extracted by expert classification system method were poor. The extracted KRD results, including KRD maps and the prediction map, both indicated that KRD areas in Puding were decreased from 1993 (spring) to 2016 (spring) and suggested to pay more attention to KRD areas changes with the seasons

Doctor of Philosophy / Department of Geography / John A. Harrington Jr / The Senegal River valley and delta (SRVD) are affected by long term climate variability. Indicators of these climatic shifts include a rainfall deficit, warmer temperatures, sea level rise, floods, and drought. These shifts have led to environmental degradation, water deficits, and profound effects on human life and activities in the area. Geographic Information Science (GIScience), including satellite-based remote sensing methods offer several advantages over conventional ground-based methods used to map and monitor salt-affected soil (SAS) features. This study was designed to assess the accuracy of information on soil salinization extracted from Landsat satellite imagery. Would available imagery and GIScience data analysis enable an ability to discriminate natural soil salinization from soil sodication and provide an ability to characterize the SAS trend and pattern over 30 years? A set of Landsat MSS (June 1973 and September 1979), Landsat TM (November 1987, April 1994 and November 1999) and ETM+ (May 2001 and March 2003) images have been used to map and monitor salt impacted soil distribution. Supervised classification, unsupervised classification and post-classification change detection methods were used. Supervised classifications of May 2001 and March 2003 images were made in conjunction field data characterizing soil surface chemical characteristics that included exchange sodium percentage (ESP), cation exchange capacity (CEC) and the electrical conductivity (EC). With this supervised information extraction method, the distribution of three different types of SAS (saline, saline-sodic, and sodic) was mapped with an accuracy of 91.07% for 2001 image and 73.21% for 2003 image. Change detection results confirmed a decreasing trend in non-saline and saline soil and an increase in saline-sodic and sodic soil. All seven Landsat images were subjected to the unsupervised classification method which resulted in maps that separate SAS according to their degree of salinity. The spatial distribution of sodic and saline-sodic soils has a strong relationship with the area of irrigated rice crop management. This study documented that human-induced salinization is progressively replacing natural salinization in the SRVD. These pedologic parameters obtained using GIScience remote sensing techniques can be used as a scientific tool for sustainable management and to assist with the implementation of environmental policy.