Functional regression on remote sensing data in oceanography

Acar-Denizli, Nihan; Delicado, Pedro; Başarır, Gülay; Caballero, Isabel

doi:10.1007/s10651-018-0405-7

Cited by 8 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We considered two classic model selection routines: Forward stepwise logistic regression (FSL [87]) using AIC [88] and Least Absolute Shrinkage and Selection Operator (LASSO) on logistic regression utilizing 10-fold cross validation [85] for covariate selection. Both are common model selection methods for remote sensing applications (e.g., [89][90][91][92][93][94][95]). We aggregated the filtered sample results by including only covariates that were selected in more than 50% of the filtered samples.…”

Section: Discussionmentioning

confidence: 99%

Advancing Cave Detection Using Terrain Analysis and Thermal Imagery

et al. 2021

View full text Add to dashboard Cite

Since the initial experiments nearly 50 years ago, techniques for detecting caves using airborne and spacecraft acquired thermal imagery have improved markedly. These advances are largely due to a combination of higher instrument sensitivity, modern computing systems, and processor-intensive analytical techniques. Through applying these advancements, our goals were to: (1) Determine the efficacy of methods designed for terrain analysis and applied to thermal imagery; (2) evaluate the usefulness of predawn and midday imagery for detecting caves; and (3) ascertain which imagery type (predawn, midday, or the difference between those two times) was most informative. Using forward stepwise logistic (FSL) and Least Absolute Shrinkage and Selection Operator (LASSO) regression analyses for model selection, and a thermal imagery dataset acquired from the Mojave Desert, California, we examined the efficacy of three well-known terrain descriptors (i.e., slope, topographic position index (TPI), and curvature) on thermal imagery for cave detection. We also included the actual, untransformed thermal DN values (hereafter “unenhanced thermal”) as a fourth dataset. Thereafter, we compared the thermal signatures of known cave entrances to all non-cave surface locations. We determined these terrain-based analytical methods, which described the “shape” of the thermal landscape, hold significant promise for cave detection. All imagery types produced similar results. Down-selected covariates per imagery type, based upon the FSL models, were: Predawn— slope, TPI, curvature at 0 m from cave entrance, as well as slope at 1 m from cave entrance; midday— slope, TPI, and unenhanced thermal at 0 m from cave entrance; and difference— TPI and slope at 0 m from cave entrance, as well as unenhanced thermal and TPI at 3.5 m from cave entrance. We provide recommendations for future research directions in terrestrial and planetary cave detection using thermal imagery.

show abstract

Section: Discussionmentioning

confidence: 99%

Advancing Cave Detection Using Terrain Analysis and Thermal Imagery

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Different machine and deep learning regressors have been used in satellite-based water quality monitoring. Table 1 provides an overview of these algorithms, which include ordinary least square (OLS)-based methods and their variants, such as simple linear regression [31], multiple linear regression (MLR) [32], polynomial regression [33], least absolute shrinkage and selection operator regression (LASSO) or L1 [34], ridge regression (RR) or L2 [35], Bayesian ridge regression (BRR) [36], and elastic net (EL) or L1&2 [37]. There are also tree-based algorithms such as decision trees (DTs) [38], boosted trees (BTs) [23], and ensemble trees, like RFs [39], included.…”

Section: An Overview Of Machine and Deep Learning Techniques Used In ...mentioning

confidence: 99%

Meta-Analysis of Satellite Observations for United Nations Sustainable Development Goals: Exploring the Potential of Machine Learning for Water Quality Monitoring

Mukonza,

Chiang

2023

Environments

View full text Add to dashboard Cite

This review paper adopts bibliometric and meta-analysis approaches to explore the application of supervised machine learning regression models in satellite-based water quality monitoring. The consistent pattern observed across peer-reviewed research papers shows an increasing interest in the use of satellites as an innovative approach for monitoring water quality, a critical step towards addressing the challenges posed by rising anthropogenic water pollution. Traditional methods of monitoring water quality have limitations, but satellite sensors provide a potential solution to that by lowering costs and expanding temporal and spatial coverage. However, conventional statistical methods are limited when faced with the formidable challenge of conducting pattern recognition analysis for satellite geospatial big data because they are characterized by high volume and complexity. As a compelling alternative, the application of machine and deep learning techniques has emerged as an indispensable tool, with the remarkable capability to discern intricate patterns in the data that might otherwise remain elusive to traditional statistics. The study employed a targeted search strategy, utilizing specific criteria and the titles of 332 peer-reviewed journal articles indexed in Scopus, resulting in the inclusion of 165 articles for the meta-analysis. Our comprehensive bibliometric analysis provides insights into the trends, research productivity, and impact of satellite-based water quality monitoring. It highlights key journals and publishers in this domain while examining the relationship between the first author’s presentation, publication year, citation count, and journal impact factor. The major review findings highlight the widespread use of satellite sensors in water quality monitoring including the MultiSpectral Instrument (MSI), Ocean and Land Color Instrument (OLCI), Operational Land Imager (OLI), Moderate Resolution Imaging Spectroradiometer (MODIS), Thematic Mapper (TM), Enhanced Thematic Mapper Plus (ETM+), and the practice of multi-sensor data fusion. Deep neural networks are identified as popular and high-performing algorithms, with significant competition from extreme gradient boosting (XGBoost), even though XGBoost is relatively newer in the field of machine learning. Chlorophyll-a and water clarity indicators receive special attention, and geo-location had a relationship with optical water classes. This paper contributes significantly by providing extensive examples and in-depth discussions of papers with code, as well as highlighting the critical cyber infrastructure used in this research. Advances in high-performance computing, large-scale data processing capabilities, and the availability of open-source software are facilitating the growing prominence of machine and deep learning applications in geospatial artificial intelligence for water quality monitoring, and this is positively contributing towards monitoring water pollution.

show abstract

“…We use Functional Data Analysis (FDA, [14]) to analyze wildfire dynamics from remote sensing data. This work is part of the growing literature on FDA for remote sensing data (see, e.g., [15][16][17] among others).…”

Section: Introductionmentioning

confidence: 99%

Wildfires Vegetation Recovery through Satellite Remote Sensing and Functional Data Analysis

2021

Self Cite

View full text Add to dashboard Cite

In recent years, wildfires have caused havoc across the world, which are especially aggravated in certain regions due to climate change. Remote sensing has become a powerful tool for monitoring fires, as well as for measuring their effects on vegetation over the following years. We aim to explain the dynamics of wildfires’ effects on a vegetation index (previously estimated by causal inference through synthetic controls) from pre-wildfire available information (mainly proceeding from satellites). For this purpose, we use regression models from Functional Data Analysis, where wildfire effects are considered functional responses, depending on elapsed time after each wildfire, while pre-wildfire information acts as scalar covariates. Our main findings show that vegetation recovery after wildfires is a slow process, affected by many pre-wildfire conditions, among which the richness and diversity of vegetation is one of the best predictors for the recovery.

show abstract

Functional regression on remote sensing data in oceanography

Cited by 8 publications

References 46 publications

Advancing Cave Detection Using Terrain Analysis and Thermal Imagery

Advancing Cave Detection Using Terrain Analysis and Thermal Imagery

Meta-Analysis of Satellite Observations for United Nations Sustainable Development Goals: Exploring the Potential of Machine Learning for Water Quality Monitoring

Wildfires Vegetation Recovery through Satellite Remote Sensing and Functional Data Analysis

Contact Info

Product

Resources

About