Estimating daily air temperature across the Southeastern United States using high-resolution satellite data: A statistical modeling study

Shi, Liuhua; Liu, Pengfei; Kloog, Itai; Lee, Mihye; Kosheleva, Anna; Schwartz, Joel

doi:10.1016/j.envres.2015.12.006

Cited by 65 publications

(39 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A direct comparison of the performance of the Antarctica T air product to other studies is difficult, not only due to differing environments and temporal scales, but most particularly due to different validation methods being used. Benali et al, Hengl et al and Shi et al [15,43,44] found considerably higher agreement between measured and predicted T air by including auxiliary variables in their models (RMSE usually below 2.5 • C). However, their model training and validation strategies do not rely on LOSOCV.…”

Section: Discussionmentioning

confidence: 99%

Mapping Daily Air Temperature for Antarctica Based on MODIS LST

et al. 2016

View full text Add to dashboard Cite

Spatial predictions of near-surface air temperature (T air ) in Antarctica are required as baseline information for a variety of research disciplines. Since the network of weather stations in Antarctica is sparse, remote sensing methods have large potential due to their capabilities and accessibility. Based on the MODIS land surface temperature (LST) data, T air at the exact time of satellite overpass was modelled at a spatial resolution of 1 km using data from 32 weather stations. The performance of a simple linear regression model to predict T air from LST was compared to the performance of three machine learning algorithms: Random Forest (RF), generalized boosted regression models (GBM) and Cubist. In addition to LST, auxiliary predictor variables were tested in these models. Their relevance was evaluated by a Cubist-based forward feature selection in conjunction with leave-one-station-out cross-validation to reduce the impact of spatial overfitting. GBM performed best to predict T air using LST and the month of the year as predictor variables. Using the trained model, T air could be estimated with a leave-one-station-out cross-validated R 2 of 0.71 and a RMSE of 10.51 • C. However, the machine learning approaches only slightly outperformed the simple linear estimation of T air from LST (R 2 of 0.64, RMSE of 11.02 • C). Using the trained model allowed creating time series of T air over Antarctica for 2013. Extending the training data by including more years will allow developing time series of T air from 2000 on.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping Daily Air Temperature for Antarctica Based on MODIS LST

et al. 2016

View full text Add to dashboard Cite

show abstract

“…So far, LM is one of the most popular statistical models for T a estimation using MODIS LST [14,17,22,25,36,37]. Although it was found that the correlation between LST and T a is high, this relationship may not actually be linear [18].…”

Section: Algorithms Usedmentioning

confidence: 99%

Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data

2017

View full text Add to dashboard Cite

Abstract:Recently, several methods have been introduced and applied to estimate daily air surface temperature (T a ) using MODIS land surface temperature data (MODIS LST). Among these methods, the most common used method is statistical modeling, and the most applied algorithms are linear/multiple linear regression models (LM). There are only a handful of studies using machine learning algorithm models such as random forest (RF) or cubist regression (CB). In particular, there is no study comparing different combinations of four MODIS LST datasets with or without auxiliary data using different algorithms such as multiple linear regression, random forest, and cubist regression for daily T a-max , T a-min , and T a-mean estimation. Our study examines the mentioned combinations of four MODIS-LST datasets and shows that different combinations and differently applied algorithms produce various T a estimation accuracies. Additional analysis of daily data from three climate stations in the mountain area of North West of Vietnam for the period of five years (2009 to 2013) with four MODIS LST datasets (AQUA daytime, AQUA nighttime, TERRA daytime, and TERRA nighttime) and two additional auxiliary datasets (elevation and Julian day) shows that CB and LM should be applied if MODIS LST data is used solely. If MODIS LST is used together with auxiliary data, especially in mountainous areas, CB or RF is highly recommended. This study proved that the very high accuracy of T a estimation (R 2 > 0.93/0.80/0.89 and RMSE~1.5/2.0/1.6 • C of T a-max , T a-min , and T a-mean , respectively) could be achieved with a simple combination of four LST data, elevation, and Julian day data using a suitable algorithm.

show abstract

“…Several studies have shown that the vegetation cover on the surface can affect LST values [53]. Vegetation cover (NDVI) data are provided every 16 days at 1-kilometer spatial resolution from the MODIS satellite, including MOD13A2 (TERRA 16-days period starting Day 001) and MYD13A2 (AQUA 16-day period starting Day 009).…”

Section: Vegetation Based On Ndvimentioning

confidence: 99%

Estimating Daily Maximum and Minimum Land Air Surface Temperature Using MODIS Land Surface Temperature Data and Ground Truth Data in Northern Vietnam

2016

View full text Add to dashboard Cite

Abstract:This study aims to evaluate quantitatively the land surface temperature (LST) derived from MODIS (Moderate Resolution Imaging Spectroradiometer) MOD11A1 and MYD11A1 Collection 5 products for daily land air surface temperature (T a ) estimation over a mountainous region in northern Vietnam. The main objective is to estimate maximum and minimum T a (T a-max and T a-min ) using both TERRA and AQUA MODIS LST products (daytime and nighttime) and auxiliary data, solving the discontinuity problem of ground measurements. There exist no studies about Vietnam that have integrated both TERRA and AQUA LST of daytime and nighttime for T a estimation (using four MODIS LST datasets). In addition, to find out which variables are the most effective to describe the differences between LST and T a , we have tested several popular methods, such as: the Pearson correlation coefficient, stepwise, Bayesian information criterion (BIC), adjusted R-squared and the principal component analysis (PCA) of 14 variables (including: LST products (four variables), NDVI, elevation, latitude, longitude, day length in hours, Julian day and four variables of the view zenith angle), and then, we applied nine models for T a-max estimation and nine models for T a-min estimation. The results showed that the differences between MODIS LST and ground truth temperature derived from 15 climate stations are time and regional topography dependent. The best results for T a-max and T a-min estimation were achieved when we combined both LST daytime and nighttime of TERRA and AQUA and data from the topography analysis.

show abstract

Estimating daily air temperature across the Southeastern United States using high-resolution satellite data: A statistical modeling study

Cited by 65 publications

References 29 publications

Mapping Daily Air Temperature for Antarctica Based on MODIS LST

Mapping Daily Air Temperature for Antarctica Based on MODIS LST

Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data

Estimating Daily Maximum and Minimum Land Air Surface Temperature Using MODIS Land Surface Temperature Data and Ground Truth Data in Northern Vietnam

Contact Info

Product

Resources

About