Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data
Noi, Phan
Degener, Jan
Kappas, Martin
9, 5: -
DOI: https://doi.org/10.3390/rs9050398
Persistent URL: http://resolver.sub.uni-goettingen.de/purl?gldocs-11858/7060
Persistent URL: http://resolver.sub.uni-goettingen.de/purl?gldocs-11858/7060
Noi, Phan; Degener, Jan; Kappas, Martin, 2017: Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data. In: Remote Sensing, Band 9, 5, DOI: 10.3390/rs9050398.
|
Dokument öffnen: |
Recently, several methods have been introduced and applied to estimate daily air surface
temperature (Ta) 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 Ta-max, Ta-min, and Ta-mean estimation. Our study examines the mentioned combinations of
four MODIS-LST datasets and shows that different combinations and differently applied algorithms
produce various Ta 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 Ta estimation (R2 > 0.93/0.80/0.89 and RMSE ~1.5/2.0/1.6 C of Ta-max, Ta-min,
and Ta-mean, respectively) could be achieved with a simple combination of four LST data, elevation,
and Julian day data using a suitable algorithm.
Statistik:
ZugriffsstatistikSammlung:
- Geologie [927]
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: