Multiple Regression Analysis for Unmixing of Surface Temperature Data in an Urban Environment

Wicki, Andreas; Parlow, Eberhard

doi:10.3390/rs9070684

Cited by 39 publications

(40 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLR is a statistical technique that uses several explanatory variables (independent variables) to predict the outcome of a response variable (dependent variable). The MLR is a widely used method to construct regression models for various applications [72,[84][85][86][87]. The goal of the MLR is to model the linear relationship between the explanatory (independent) variables and response (dependent) variable (FSV).…”

Section: Statistical Models For Estimating the Fsvmentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The forest stock volume (FSV) is one of the key indicators in forestry resource assessments on local, regional, and national scales. To date, scaling up in situ plot-scale measurements across landscapes is still a great challenge in the estimation of FSVs. In this study, Sentinel-2 imagery, the Google Earth Engine (GEE) cloud computing platform, three base station joint differential positioning technology (TBSJDPT), and three algorithms were used to build an FSV model for forests located in Hunan Province, southern China. The GEE cloud computing platform was used to extract the imagery variables from the Sentinel-2 imagery pixels. The TBSJDPT was put forward and used to provide high-precision positions of the sample plot data. The random forests (RF), support vector regression (SVR), and multiple linear regression (MLR) algorithms were used to estimate the FSV. For each pixel, 24 variables were extracted from the Sentinel-2 images taken in 2017 and 2018. The RF model performed the best in both the training phase (i.e., R 2 = 0.91, RMSE = 35.13 m 3 ha −1 , n = 321) and in the test phase (i.e., R 2 = 0.58, RMSE = 65.03 m 3 ha −1 , and n = 138). This model was followed by the SVR model (R 2 = 0.54, RMSE = 65.60 m 3 ha −1 , n = 321 in training; R 2 = 0.54, RMSE = 66.00 m 3 ha −1 , n = 138 in testing), which was slightly better than the MLR model (R 2 = 0.38, RMSE = 75.74 m 3 ha −1 , and n = 321 in training; R 2 = 0.49, RMSE = 70.22 m 3 ha −1 , and n = 138 in testing) in both the training phase and test phase. The best predictive band was Red-Edge 1 (B5), which performed well both in the machine learning methods and in the MLR method. The Blue band (B2), Green band (B3), Red band (B4), SWIR2 band (B12), and vegetation indices (TCW, NDVI_B5, and TCB) were used in the machine learning models, and only one vegetation index (MSI) was used in the MLR model. We mapped the FSV distribution in Hunan Province (3.50 × 10 8 m 3 ) based on the RF model; it reached a total accuracy of 63.87% compared with the official forest report in 2017 (5.48 × 10 8 m 3 ). The results from this study will help develop and improve satellite-based methods to estimate FSVs on local, regional and national scales.The forest stock volume (FSV, m 3 ha −1 ) is the sum of the stem volumes of all the living trees per unit area, and is one of key forest variables for forest resources management and assessments on local, region and country scales [1]. FSVs have a strong relationship with the aboveground biomass (AGB) and carbon stocks [2]. To understand the spatial distribution of carbon in forests and to derive predictions for monitoring carbon stock trends, the FSV must be quantified [3]. Traditionally, the FSV is estimated by sampling several plots, which involves substantial manpower, materials, and financial resources [4]. With the development of remote sensing technology, particularly the Landsat series since 1972, satellite imagery has played an important role in forest inventory. Various studies have been performed to estimate the forest variables ...

show abstract

Section: Statistical Models For Estimating the Fsvmentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Previous studies have mainly focused on studying differences in ground temperatures as a function of land-use land cover and its evolution at the city level [16,16,20,[33][34][35], temporal trends in urban SUHI in urban areas [18,36,37], the refreshing impact of parks on their surroundings [15,38,39], the evolution of SUHI as a function of day and night [9,34,40,41], the impact of vegetation on LST at the urban scale [12,36,37,42], comparison of surface temperatures and air temperature [8][9][10]20,43,44], the impact of surface temperatures on health [30,41] and transversely at surface temperatures at moderate resolutions (MODIS 1 km) [16,20,[34][35][36]42,45] but, to our knowledge, there are no similar studies such as ours that analyze the thermal monitoring of site redevelopment at such a detailed spatial and temporal resolution.…”

Section: Introductionmentioning

confidence: 99%

“…Fully vegetated pixels (NDVI > NDVI V ) have an emissivity value of 0.99 (ε vλ ), and soil pixels (NDVI < NDVI S ) a value of 0.96 (ε sλ ). Wicki and Parlow (2017) [33] proposed a more sophisticated approach for urban areas based on the NDVI THM to estimate land-surface emissivity using the Normalized Difference Water Index (NDWI) [73] and Normalized Difference Built-Up Index (NDBI) [74].…”

mentioning

confidence: 99%

“…One of the many advantages of the SC algorithm is the correction of atmospheric influence to remove the atmospheric effects occurring between Earth's surface and satellite sensors [33]. To this end, it is necessary to know site-specific atmospheric parameters: atmospheric transmissivity τ, upwelling atmospheric radiance L ↑ , and downwelling atmospheric radiance L ↓ .…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of the Effect of Urban Redevelopment on Surface Urban Heat Islands

et al. 2019

View full text Add to dashboard Cite

Climate change is a global challenge with multiple consequences. One of its impacts is the increase in heatwave frequency and intensity. The risk is higher for populations living in urban areas, where the highest temperatures are generally identified, due to the urban heat island effect. This phenomenon has recently been taken into account by local elected officials. As a result, developers have decided to use solutions in redevelopment projects to combat high temperatures in urban areas. Consequently, the objective is to study the land-surface temperature evolution of six main urban redevelopments in Lyon, France, from 2000 to 2017. Three of them (the Confluence, Kaplan, and Museum sites) were composed of industrial areas that have undergone major transformations and are now tertiary or residential areas. Two sites have been more lightly transformed, particularly by increasing vegetation to reduce heat stress and urban flooding (Dock and Garibaldi Street). Finally, the Groupama Stadium has been built into agricultural and wooded areas. Changes in vegetation cover (NDVI), water (MNDWI), and moisture (NDMI) content, built areas (NDBI) and bare soil (NDBaI) are also monitored. The results show that the Confluence and Kaplan sites were accompanied by a decrease in surface temperature and an increase in vegetation and moisture, whereas the Groupama Stadium displayed a rise in surface temperature and a decrease in vegetation. On the other hand, the Museum, Dock, and Garibaldi sites did not exhibit clear and uniform trends, although an increase in surface temperature was shown in some statistical tests. The disparity of the results shows the necessity to include a significant amount of vegetation during redevelopment operations in order to reduce heat stress.

show abstract

“…This knowledge depends directly on the density of the measurement network. This is not a new phenomenon and multiple studies have studied this question, through classical spatial interpolations (deterministic [9] or stochastic [9,10]) or multiple regressions [11][12][13][14][15], for example. This issue is very important in the context of climate change and the rise of heat waves, particularly with the closure of several Météo-France measurement stations [16,17].…”

Section: Introductionmentioning

confidence: 99%

Integrating Satellite-Derived Data as Spatial Predictors in Multiple Regression Models to Enhance the Knowledge of Air Temperature Patterns

Alonso

Renard

2019

Urban Science

View full text Add to dashboard Cite

With the phenomenon of urban heat island and thermal discomfort felt in urban areas, exacerbated by climate change, it is necessary to best estimate the air temperature in every part of an area, especially in the context of the on-going rationalization weather stations network. In addition, the comprehension of air temperature patterns is essential for multiple applications in the fields of agriculture, hydrology, land development or public health. Thus, this study proposes to estimate the air temperature from 28 explanatory variables, using multiple linear regressions. The innovation of this study is to integrate variables from remote sensing into the model in addition to the variables traditionally used like the ones from the Land Use Land Cover. The contribution of spectral indices is significant and makes it possible to improve the quality of the prediction model. However, modeling errors are still present. Their locations and magnitudes are analyzed. However, although the results provided by modelling are of good quality in most cases, particularly thanks to the introduction of explanatory variables from remote sensing, this can never replace dense networks of ground-based measurements. Nevertheless, the methodology presented, applicable to any territory and not requiring specific computer resources, can be highly useful in many fields, particularly for urban planners.

show abstract

Multiple Regression Analysis for Unmixing of Surface Temperature Data in an Urban Environment

Cited by 39 publications

References 78 publications

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Evaluation of the Effect of Urban Redevelopment on Surface Urban Heat Islands

Integrating Satellite-Derived Data as Spatial Predictors in Multiple Regression Models to Enhance the Knowledge of Air Temperature Patterns

Contact Info

Product

Resources

About