Abstract
Monitoring evapotranspiration (ET) is possible through land surface temperature (LST) measured by satellites and unmanned aerial vehicles (UAV). The assumption that the higher resolution of LST may improve the performance of remote sensing ET models was verified in a recently published article showing that higher resolution LST led to increased performance of the Two-source Energy Balance Model (TSEB)—one of the well-known ET models. However, because of technology limitations, the spatial resolutions of satellite and UAV thermal imagery are coarser than those in optical and near-infrared (NIR) bands. Therefore, developing thermal sharpening techniques and assessing their impacts on ET models performance are imperative. Although previous studies have developed and evaluated downscaling LST methods for satellite imagery, implementation of those methods on UAV imagery is limited. In this study, a coupled wavelet, machine learning, and optimization algorithm was implemented for downscaling UAV thermal imagery from 60 cm to the resolution of UAV optical imagery (15 cm) because 60 cm pixel resolution still incorporate mixed temperatures from the soil, vine canopy, active cover crop and shaded regions. A 2D discrete wavelet transform (2D DWT) was employed for the decomposition of inputs to 60 cm and inverse transformation of low thermal resolution to higher resolution. Four machine-learning-based algorithms (Decision Tree Regression (DTR), Ensemble Decision Tree (DTER), Support Vector Machine (SVM), and Gaussian process regression (GPR)) along with four linear regression-based models (linear, interactions linear, robust linear and stepwise linear) are used as the potential fitting models, and a grid search algorithm is used for auto-tuning parameters of the machine learning algorithms. Additionally, a novel sampling technique was designed to provide more representative samples for training steps in the regressing models. Four sets of high-resolution images were provided by the Utah State University AggieAir sUAS Program as part of the ARS-USDA GRAPEX Project collected since 2014 over multiple vineyards located in California. After applying the proposed downscaling algorithm, a separation method was used for estimation of canopy and soil temperatures from the original and sharpened thermal imagery. Ultimately, the TSEB model was executed for these pairs of temperature components, and its performance compared to eddy covariance measurements. Results demonstrated that the proposed sampling algorithm can significantly accelerate the computation time for the UAV temperature sharpening efforts. Among all the fitting models, GPR, SVM and DTER were the most accurate in terms of R-square. GPR, SVM and DTER’s \(R^2\) were higher than 90% for all cases. The correlation between NDVI and radiometric temperature (Tr) was significantly improved when the downscaled Tr (DTr) was used in the NDVI–Tr domain for the separation procedure. Compared to additional IRT sensors temperatures, Tc and particularly Ts derived from the DTr were closer to the observed measurements. After feeding the TSEB model with DTr products, results demonstrated that estimations of soil heat flux (G) were significantly improved, while large LE differences were reduced (from 20.26 to 13.5 in terms of RRMSE).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aboutalebi M et al. (2018) Assessment of Landsat Harmonized sUAS Reflectance Products Using Point Spread Function (PSF) on Vegetation Indices (VIs) and Evapotranspiration (ET) Using the Two-Source Energy Balance (TSEB) Model. In: AGU Fall Meeting Abstracts
Aboutalebi M et al. (2019) Incorporation of Unmanned Aerial Vehicle (UAV) Point Cloud Products into Remote Sensing Evapotranspiration Models. In: Remote Sensing 12.1. issn: 2072-4292. https://doi.org/10.3390/rs12010050. https://www.mdpi.com/2072-4292/12/1/50
Aboutalebi M (2018) Discussion of Equation to Predict Riverine Transport of Suddenly Discharged Pollutants; by Mostafa Farhadian, Omid Bozorg-Haddad, Samaneh Seifollahi-Aghmiuini, and Hugo A. Loiciga. In: Journal of Irrigation and Drainage Engineering 144.4, p. 07018010. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001269
Aboutalebi M, Bozorg Haddad O, Loáiciga HA (2015) Optimal Monthly Reservoir Operation Rules for Hydropower Generation Derived with SVR-NSGAII. In: Journal of Water Resources Planning and Management 141.11, p. 04015029. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000553
Aboutalebi M, Bozorg HO, Loáiciga HA (2016) Application of the SVR-NSGAII to Hydrograph Routing in Open Channels. In: Journal of Irrigation and Drainage Engineering 142.3, p. 04015061. https://doi.org/10.1061/(ASCE)IR.1943-4774.0000969
Agam Nurit et al. (2007) A vegetation index based technique for spatial sharpening of thermal imagery. In: Remote Sensing of Environment 107.4, pp. 545–558. issn: 0034-4257. https://doi.org/10.1016/j.rse.2006.10.006. http://www.sciencedirect.com/science/article/pii/S0034425706003671
AgiSoft LLC, Petersburg Russia St (2016) Agisoft photoscan. Version Professional Edition. In: ()
Anderson MC et al. (2004) A Multiscale Remote Sensing Model for Disaggregating Regional Fluxes to Micrometeorological Scales. In: Journal of Hydrometeorology 5.2, pp. 343–363. https://doi.org/10.1175/1525-7541(2004)005<0343:AMRSMF>2.0.CO;2
Bechtel B, Zakšek K, Hoshyaripour G (2012) Downscaling Land Surface Temperature in an Urban Area: A Case Study for Hamburg, Germany. In: Remote Sensing 4.10, pp. 3184-3200. issn: 2072-4292. https://doi.org/10.3390/rs4103184. https://www.mdpi.com/2072-4292/4/10/3184
Bindhu VM, Narasimhan B, Sudheer KP (2013) Development and verification of a non-linear disaggregation method (NL-DisTrad) to down792 scale MODIS land surface temperature to the spatial scale of Landsat thermal data to estimate evapotranspiration. In: Remote Sensing of Environment 135, pp. 118–129. issn: 0034-4257. https://doi.org/10.1016/j.rse.2013.03.023. url: http://www.sciencedirect.com/science/article/pii/S0034425713001028
Bonafoni S (2016) Downscaling of Landsat and MODIS Land Surface Temperature Over the Heterogeneous Urban Area of Milan. In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 9.5, pp. 2019–2027. issn: 2151-1535. https://doi.org/10.1109/JSTARS.2016.2514367
Bruce LM, Koger CH, Li Jiang (2002) Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction. In: IEEE Transactions on Geoscience and Remote Sensing 40.10, pp. 2331–2338. issn: 1558-0644. https://doi.org/10.1109/TGRS.2002.804721
Brunsell NA, Gillies RR (2003) Determination of scaling characteristics of AVHRR data with wavelets: Application to SGP97. In: International Journal of Remote Sensing 24.14, pp. 2945–2957. https://doi.org/10.1080/01431160210155983
Chen S et al. (2008) Fusing remote sensing images using à trous wavelet transform and empirical mode decomposition. In: Pattern Recognition Letters 29.3, pp. 330–342. issn: 0167-8655. https://doi.org/10.1016/j.patrec.2007.10.013.968. http://www.sciencedirect.com/science/article/pii/S0167865507003285
Cohen A (1994) Ten Lectures on Wavelets, CBMS-NSF Regional Conference Series in Applied Mathematics, Vol. 61, I. Daubechies, SIAM, 1992, xix + 357 pp. In: Journal of Approximation Theory 78.3, pp. 460–461. issn: 0021-9045. https://doi.org/10.1006/jath.1994.1093. http://www.sciencedirect.com/science/article/pii/S0021904584710938
Crowther BG (1992) Radiometric calibration of multispectral video imagery. PhD thesis. Utah State University
Dennison Philip E et al (2006) Wildfire temperature and land cover modeling using hyperspectral data. In: Remote Sensing of Environment 100.2, pp. 212–222. issn: 0034-4257. https://doi.org/10.1016/j.rse.2005.10.007. http://www.sciencedirect.com/science/article/pii/S0034425705003536
Despotovic M et al. (2016) Evaluation of empirical models for predicting monthly mean horizontal diffuse solar radiation. In: Renewable and Sustainable Energy Reviews 56, pp. 246–260. issn: 1364-0321. https://doi.org/10.1016/j.rser.2015.11.058. http://www.sciencedirect.com/science/article/pii/S1364032115013258
Ebden M (2008) Gaussian processes for regression: a quick introduction
Elarab M et al. (2015) Estimating chlorophyll with thermal and broad band multispectral high resolution imagery from an unmanned aerial system using relevance vector machines for precision agriculture. In: International Journal of Applied Earth Observation and Geoinformation 43, pp. 32–42. issn: 0303-2434. https://doi.org/10.1016/j.jag.2015.03.017. url: http://www.sciencedirect.com/science/article/pii/S0303243415000719
Essa W et al. (2013) Downscaling of thermal images over urban areas using the land surface temperature-impervious percentage relationship. In: International Journal of Applied Earth Observation and Geoinformation 23, pp. 95–108. issn: 0303-2434. https://doi.org/10.1016/j.jag.2012.12.007. http://www.sciencedirect.com/science/article/pii/S0303243412002474
Gao F, Kustas William P, Anderson Martha C (2012) A Data Mining Approach for Sharpening Thermal Satellite Imagery over Land. In: Remote Sensing 4.11, pp. 3287–3319. issn: 2072-4292. https://doi.org/10.3390/rs4113287. https://www.mdpi.com/2072-4292/4/11/3287
Gs C, Norman JM (2000) An Introduction to Environmental Biophysics. Springer, New York, Modern Acoustics and Signal isbn:9780387949376. https://books.google.com/books?id=v6UpE6lThCwC
Inamdar AK et al. (2008) Land surface temperature retrieval at high spatial and temporal resolutions over the southwestern United States. In: Journal of Geophysical Research: Atmospheres 113.D7. https://doi.org/10.1029/2007JD009048. https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2007JD009048
Inamdar AK, French A (2009) Disaggregation of GOES land surface temperatures using surface emissivity. In: Geophysical Research Letters 36.2. https://doi.org/10.1029/2008GL036544. https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2008GL036544
Kaheil YH et al. (2008) Downscaling and Forecasting of Evapotranspiration Using a Synthetic Model of Wavelets and Support Vector Machines. In: IEEE Transactions on Geoscience and Remote Sensing 46.9, pp. 2692–2707. issn: 0196-2892. https://doi.org/10.1109/TGRS.2008.919819
Kumar P, Foufoula-Georgiou E (1993) A multicomponent decom position of spatial rainfall fields: 1. Segregation of large- and small-scale features using wavelet transforms. In: Water Resources Research 29.8, pp. 2515–2532. https://doi.org/10.1029/93WR00548
Kustas William P et al. (2003) Estimating subpixel surface temperatures and energy fluxes from the vegetation index-radiometric temperature relationship. In: Remote Sensing of Environment 85.4, pp. 429–440. issn: 0034-4257. https://doi.org/10.1016/S0034-4257(03)00036-1. http://www.sciencedirect.com/science/article/pii/S0034425703000361
Kustas WP et al. (2018) The Grape Remote Sensing Atmospheric Profile and Evapotranspiration Experiment. In: Bulletin of the American Meteorological Society 99.9 (2018), pp. 1791–1812. https://doi.org/10.1175/BAMSD-16-0244.1
Kustas WP, Norman JM (1999) Evaluation of soil and vegetation heat flux predictions using a simple two-source model with radiometric temperatures for partial canopy cover. In: Agricultural and Forest Meteorology 94.1, pp. 13–29. issn: 0168-1923. https://doi.org/10.1016/S0168-1923(99)00005-2. http://www.sciencedirect.com/science/article/pii/S0168192399000052
Li B, Yang R, Jiang H (2011) Remote-Sensing Image Compression Using Two-Dimensional Oriented Wavelet Transform. In: IEEE Transactions on Geoscience and Remote Sensing 49.1, pp. 236–250. issn: 1558-0644. https://doi.org/10.1109/TGRS.2010.2056691
Li M-F et al. (2013) General models for estimating daily global solar radiation for different solar radiation zones in mainland China. In: Energy Conversion and Management 70, pp. 139–148. issn: 0196-8904. https://doi.org/10.1016/j.enconman.2013.03.004. http://www.sciencedirect.com/science/article/pii/S0196890413001118
Liu H, Wang L, Jezek KC (2005) Wavelet-transform based edge detection approach to derivation of snowmelt onset, end and duration from satellite passive microwave measurements. In: International Journal of Remote Sensing 26.21, pp. 4639–4660. https://doi.org/10.1080/01431160500213342
Miura T, Huete AR (2009) Performance of three reflectance calibration methods for airborne hyperspectral spectrometer data. In: Sensors (Basel) 9.2, pp. 794–813. https://doi.org/10.3390/s90200794
Neale Christopher MU, Crowther Blake G (1994) An airborne multispectral video/radiometer remote sensing system: Development and calibration. In: Remote Sensing of Environment 49.3, pp. 187–194. issn: 0034-4257. https://doi.org/10.1016/0034-4257(94)90014-0. http://www.sciencedirect.com/science/article/pii/0034425794900140
Nemani R et al. (1993) Developing Satellite-derived Estimates of SurfaceMoisture Status. In: Journal of Applied Meteorology 32.3, pp. 548–557. https://doi.org/10.1175/1520-0450(1993)032<0548:DSDEO>2.0.CO;2
Nieto H et al. (2019) Evaluation of TSEB turbulent fluxes using different methods for the retrieval of soil and canopy component temperatures from UAV thermal and multispectral imagery. In: Irrigation Science 37.3, pp. 389–406. issn: 1432-1319. https://doi.org/10.1007/s00271-018-0585-9
Pelgrum H et al. (2000) Length-Scale analysis of surface albedo, temperature, and normalized difference vegetation index in desert grassland. In: Water Resources Research 36.7, pp. 1757–1765. https://doi.org/10.1029/2000WR900028. https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2000WR900028
Rasmussen CE, Williams CKI (2006) Gaussian Processes for Machine Learning. Adaptive Computation and Machine Learning. Cambridge, MA, USA: MIT Press, p. 248
Schulz E, Speekenbrink M, Krause A (2018) A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. In: Journal of Mathematical Psychology 85, pp. 1–16. issn: 0022-2496. https://doi.org/10.1016/j.jmp.2018.03.001. http://www.sciencedirect.com/science/article/pii/S0022249617302158
Song C, Jia L, Menenti M (2014) Retrieving High-Resolution Surface Soil Moisture by Downscaling AMSR-E Brightness Temperature Using MODIS LST and NDVI Data. In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 7.3, pp. 935–942. issn: 2151-1535. https://doi.org/10.1109/JSTARS.2013.2272053.
Strahler Alan H, Woodcock Curtis E, Smith James A (1986) On the nature of models in remote sensing. In: Remote Sensing of Environment 20.2, pp. 121–139. issn: 0034-4257. https://doi.org/10.1016/0034-4257(86)90018-0. http://www.sciencedirect.com/science/ article/pii/0034425786900180
Tello Alonso M et al. (2011) Edge Enhancement Algorithm Based on the Wavelet Transform for Automatic Edge Detection in SAR Images. In: IEEE Transactions on Geoscience and Remote Sensing 49.1, pp. 222–235. issn: 1558-0644. https://doi.org/10.1109/TGRS.2010.2052814
Torres-Rua A (2017) Vicarious Calibration of sUAS Microbolometer Temperature Imagery for Estimation of Radiometric Land Surface Temperature. In: Sensors 17.7. issn: 1424-8220. https://doi.org/10.3390/s17071499. https://www.mdpi.com/1424-8220/17/7/1499
Twine TE et al (2000) Correcting eddy-covariance flux underestimates over a grassland. In: Agricultural and Forest Meteorology 103.3, pp. 279–300. issn: 0168-1923. https://doi.org/10.1016/S0168-1923(00)00123-4. http://www.sciencedirect.com/science/article/pii/S0168192300001234
Vapnik Vladimir N (1995) The Nature of Statistical Learning Theory. Springer, Berlin
Vladimir NV (1998) Interscience, statistical learning theory. Wiley, Amsterdam
Voogt JA, Oke TR (2003) Thermal remote sensing of urban climates. In: Remote Sensing of Environment 86.3. Urban Remote Sensing, pp. 370–384. issn: 0034-4257. https://doi.org/10.1016/S0034-4257(03)00079-8. http://www.sciencedirect.com/science/article/ pii/S0034425703000798
White William A et al (2018) Determining a robust indirect measurement of leaf area index in California vineyards for validating remote sensing based retrievals. Irrig Sci 37:269–280
Willmott Cort J, Matsuura Kenji (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. In: Climate Research 30.1, pp. 79–82. https://doi.org/10.3354/cr030079. https://www.int-res.com/abstracts/cr/v30/n1/p79-82/
Yang G et al. (2011) Estimation of subpixel land surface temperature using an endmember index based technique: A case examination on ASTER and MODIS temperature products over a heterogeneous area. In: Remote Sensing of Environment 115.5, pp. 1202–1219. issn: 0034-4257. https://doi.org/10.1016/j.rse.2011.01.004. http://www.sciencedirect.com/science/article/pii/S0034425711000174
Yang G et al. (2010) A Novel Method to Estimate Subpixel Temperature by Fusing Solar-Re ective and Thermal-Infrared Remote-Sensing Data With an Artificial Neural Network. In: IEEE Transactions on Geoscience and Remote Sensing 48.4, pp. 2170–2178. issn: 1558- 0644. https://doi.org/10.1109/TGRS.2009.2033180.
Zakšek K, Oštir K (2012) Downscaling land surface temperature for urban heat island diurnal cycle analysis. In: Remote Sensing of Environment 117. Remote Sensing of Urban Environments, pp. 114–124. issn: 0034-4257. https://doi.org/10.1016/j.rse.2011.05.027. http://www.sciencedirect.com/science/article/pii/ S0034425711002872
Zhan W et al. (2013) Disaggregation of remotely sensed land surface temperature: Literature survey, taxonomy, issues, and caveats. In: Re- mote Sensing of Environment 131, pp. 119–139. issn: 0034-4257. https://doi.org/10.1016/j.rse.2012.12.014. http://www.sciencedirect.com/science/article/pii/S0034425712004804
Zhou J, Civco DL, Silander JA (1998) A wavelet transform method to merge Landsat TM and SPOT panchromatic data. In: International Journal of Remote Sensing 19.4, pp. 743–757. https://doi.org/10.1080/014311698215973
Acknowledgements
E.& J. Gallo Winery and Utah State Water Research Laboratory contributed towards the acquisition and processing of the ground truth and UAV imagery data collected during GRAPEX Intensive Observation Periods (IOPs). In addition, we would like to thank the staff of Viticulture, Chemistry and Enology Division of E. &J. Gallo Winery for the assistance in the collection and processing of field data during GRAPEX IOPs. Finally, this project would not have been possible without the cooperation of Ernie Dosio of Pacific Agri Lands Management, along with the Sierra Loma vineyard staff, for logistical support of GRAPEX field and research activities. The authors would like to thank Carri Richards for editing the manuscript. Finally, we would like to acknowledge the significant financial support for this research from the NASA Applied Sciences-Water Resources NNX17AF51G Project. USDA is an equal opportunity provider and employer.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Aboutalebi, M., Torres-Rua, A.F., McKee, M. et al. Downscaling UAV land surface temperature using a coupled wavelet-machine learning-optimization algorithm and its impact on evapotranspiration. Irrig Sci 40, 553–574 (2022). https://doi.org/10.1007/s00271-022-00801-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00271-022-00801-2