67 research outputs found
Urban climate characterization and heat risk assessment based on machine learning and remote sensing data
No full textDepartment of Urban and Environmental Engineering (Environmental Science and Engineering)clos
All-Sky 1 km MODIS Land Surface Temperature Reconstruction Considering Cloud Effects Based on Machine Learning
No full textOpen AccessArticle
All-Sky 1 km MODIS Land Surface Temperature Reconstruction Considering Cloud Effects Based on Machine Learning
by Dongjin ChoORCID,Dukwon Bae,Cheolhee YooORCID,Jungho Im *ORCID,Yeonsu LeeORCID andSiwoo LeeORCID
Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan 44919, Korea
*
Author to whom correspondence should be addressed.
Academic Editor: Anand Inamdar
Remote Sens. 2022, 14(8), 1815; https://doi.org/10.3390/rs14081815
Received: 9 February 2022 / Revised: 5 April 2022 / Accepted: 7 April 2022 / Published: 9 April 2022
(This article belongs to the Special Issue Land Surface Temperature Estimation Using Remote Sensing)
Download PDF Browse Figures Citation Export
Abstract
A high spatio-temporal resolution land surface temperature (LST) is necessary for various research fields because LST plays a crucial role in the energy exchange between the atmosphere and the ground surface. The moderate-resolution imaging spectroradiometer (MODIS) LST has been widely used, but it is not available under cloudy conditions. This study proposed a novel approach for reconstructing all-sky 1 km MODIS LST in South Korea during the summer seasons using various data sources, considering the cloud effects on LST. In South Korea, a Local Data Assimilation and Prediction System (LDAPS) with a relatively high spatial resolution of 1.5 km has been operated since 2013. The LDAPS model???s analysis data, binary MODIS cloud cover, and auxiliary data were used as input variables, while MODIS LST and cloudy-sky in situ LST were used together as target variables based on the light gradient boosting machine (LightGBM) approach. As a result of spatial five-fold cross-validation using MODIS LST, the proposed model had a coefficient of determination (R2) of 0.89???0.91 with a root mean square error (RMSE) of 1.11???1.39 ??C during the daytime, and an R2 of 0.96???0.97 with an RMSE of 0.59???0.60 ??C at nighttime. In addition, the reconstructed LST under the cloud was evaluated using leave-one-station-out cross-validation (LOSOCV) using 22 weather stations. From the LOSOCV results under cloudy conditions, the proposed LightGBM model had an R2 of 0.55???0.63 with an RMSE of 2.41???3.00 ??C during the daytime, and an R2 of 0.70???0.74 with an RMSE of 1.31???1.36 ??C at nighttime. These results indicated that the reconstructed LST has higher accuracy than the LDAPS model. This study also demonstrated that cloud cover information improved the cloudy-sky LST estimation accuracy by adequately reflecting the heterogeneity of the relationship between LST and input variables under clear and cloudy skies. The reconstructed all-sky LST can be used in a variety of research applications including weather monitoring and forecasting
Estimation of maximum and minimum air temperatures in urban areas using MODIS satellite data
No full textCooperative protein structural dynamics of homodimeric hemoglobin linked to water cluster at subunit interface revealed by time-resolved X-ray solution scattering
No full textHomodimeric hemoglobin (HbI) consisting of two subunits is a good model system for investigating the allosteric structural transition as it exhibits cooperativity in ligand binding. In this work, as an effort to extend our previous study on wild-type and F97Y mutant HbI, we investigate structural dynamics of a mutant HbI in solution to examine the role of well-organized interfacial water cluster, which has been known to mediate intersubunit communication in HbI. In the T72V mutant of HbI, the interfacial water cluster in the T state is perturbed due to the lack of Thr72, resulting in two less interfacial water molecules than in wild-type HbI. By performing picosecond time-resolved X-ray solution scattering experiment and kinetic analysis on the T72V mutant, we identify three structurally distinct intermediates (I1, I2, and I3) and show that the kinetics of the T72V mutant are well described by the same kinetic model used for wild-type and F97Y HbI, which involves biphasic kinetics, geminate recombination, and bimolecular CO recombination. The optimized kinetic model shows that the R-T transition and bimolecular CO recombination are faster in the T72V mutant than in the wild type. From structural analysis using species-associated difference scattering curves for the intermediates, we find that the T-like deoxy I3 intermediate in solution has a different structure from deoxy HbI in crystal. In addition, we extract detailed structural parameters of the intermediates such as E-F distance, intersubunit rotation angle, and heme-heme distance. By comparing the structures of protein intermediates in wild-type HbI and the T72V mutant, we reveal how the perturbation in the interfacial water cluster affects the kinetics and structures of reaction intermediates of HbI. © 2016 Author(s)1571sciescopu
High-Resolution Seamless Daily Sea Surface Temperature Based on Satellite Data Fusion and Machine Learning over Kuroshio Extension
No full textSea SurfaceTemperature (SST) is a critical parameter for monitoring the marine environment and understanding various ocean phenomena. While SST can be regularly retrieved from satellite data, it often suffers from missing data due to various reasons including cloud contamination. In this study, we proposed a novel two-step data fusion framework for generating high-resolution seamless daily SST from multi-satellite data sources. The proposed approach consists of (1) SST reconstruction based on Data Interpolate Convolutional AutoEncoder (DINCAE) using the SSTs derived from two satellite sensors (i.e., Moderate Resolution Imaging Spectroradiometer (MODIS) and Advanced Microwave Scanning Radiometer 2(AMSR2)), and (2) SST improvement through data fusion using random forest for consistency with in situ measurements with two schemes (i.e., scheme 1 using the reconstructed MODIS SST variables and scheme 2 using both MODIS and AMSR2 SST variables). The proposed approach was evaluated over the Kuroshio Extension in the Northwest Pacific, where a highly dynamic SST pattern can be found, from 2015 to 2019. The results showed that the reconstructed MODIS and AMSR2 SSTs through DINCAE yielded very good performance with Root Mean Square Errors (RMSEs) of 0.85 and 0.60 degrees C and Mean Absolute Errors (MAEs) of 0.59 and 0.45 degrees C, respectively. The results from the second step showed that scheme 2 and scheme 1 produced RMSEs of 0.75 and 0.98 degrees C and MAEs of 0.53 and 0.68 degrees C, respectively, compared to the in situ measurements, which proved the superiority of scheme 2 using multi-satellite data sources. Scheme 2 also showed comparable or even better performance than two operational SST products with similar spatial resolution. In particular, scheme 2 was good at simulating features with fine resolution (~50 km). The proposed approach yielded promising results over the study area, producing seamless daily SST products with high quality and high feature resolution
Improving forecasting performance of urban air temperature using in-situ and satellite observations and numerical weather prediction model output
No full textMapping 10-m Industrial Lands across 1000+ Global Large Cities, 2017–2023
No full textAbstract Industrial lands, as a key component of economic development, pose great environmental challenges, which underscores the need for close global monitoring to support sustainable urban development. Despite this importance, global city-level maps of industrial land use, especially over multiple years, have been lacking. Here, we present a 10-m resolution global dataset tracking industrial land use in 1,093 large cities (area 100 km² or more) from 2017 to 2023. Using multisource geospatial data and machine learning, the dataset achieves a high overall accuracy of 91.87% to 92.21% across the seven-year period, aligning well with official city maps. We further validated its reliability by computing industrial land area per capita for 1,093 cities, which correlated strongly with per capita CO2 emissions (r = 0.72). These maps offer a valuable tool for tracking industrial land use changes and assessing their impact on urban ecosystems. The dataset is a critical resource for studying the links between industrialization, urbanization, and environmental sustainability while providing insights to policymakers on balancing economic and environmental priorities
Identifying the Impact of Regional Meteorological Parameters on US Crop Yield at Various Spatial Scales Using Remote Sensing Data
No full textThis study investigates the influence of meteorological parameters such as temperature and precipitation on gross primary production (GPP) in the continental United States (CONUS) during boreal summer using satellite-based temperature and precipitation indices and GPP data at various scales (i.e., pixel, county, and state levels). The strong linear relationship between temperature and precipitation indices is presented around the central United States, particularly in the Great Plains, where the year-to-year variation of GPP is very sensitive to meteorological conditions. This sensitive GPP variation is mostly attributable to the semi-arid climate in the Great Plains, where crop productivity and temperature are closely related. The more specific information for the regionality of the relationships across the variables manifests itself at higher resolutions. The impact of the summer meteorological condition on the annual crop yield is particularly significant. Maize and soybean yields show a strong correlation with both Temperature Condition Index (TCI) and Precipitation Condition Index (PCI) in the Great Plains, with a relatively higher relationship with TCI than PCI, which is consistent with the relationship compared with GPP. This study suggests that in-depth investigations into the relationship between maize and soybean yields and the climate are required. The region-dependent relationship between GPP and meteorological conditions in our study would guide agricultural decision making in the future climate
Improvement of spatial interpolation accuracy of daily maximum air temperature in urban areas using a stacking ensemble technique
No full textThe reliable and robust monitoring of air temperature distribution is essential for urban thermal environmental analysis. In this study, a stacking ensemble model consisting of multi-linear regression (MLR), support vector regression (SVR), and random forest (RF) optimized by the SVR is proposed to interpolate the daily maximum air temperature (T-max) during summertime in a mega urban area. A total of 10 geographic variables, including the clear-sky averaged land surface temperature and the normalized difference vegetation index, were used as input variables. The stacking model was compared to Cokriging, three individual data-driven methods, and a simple average ensemble model, all through leave-one-station-out cross validation. The stacking model showed the best performance by improving the generalizability of the individual models and mitigating the sensitivity to the extreme daily T-max. This study demonstrates that the stacking ensemble method can improve the accuracy of spatial interpolation of environmental variables in various research fields
Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea
No full textNear-surface relative humidity (RHns) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RHns estimation is difficult due to the spatial discontinuity of in situ observations and the cloud contamination of satellite-based data. This article proposed machine learning-based models to estimate spatially continuous daily RHns at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RHns. All sky estimation of RHns using machine learning has been rarely conducted, and it can be an alternative to the currently available RHns data mostly from numerical models, which have relatively low spatial resolution. We combined two schemes for clear sky conditions (scheme A, which uses satellite and reanalysis data) and cloudy sky conditions (scheme B, which uses reanalysis data solely). The relatively small numbers of data in extremely low and high RHns conditions (i.e., <30% or >70%, respectively) were augmented by applying an oversampling method to avoid biased training. The machine learning models based on random forest (RF) and XGBoost were trained and validated using 94 in situ observation sites from meteorological administrations of both countries from 2012 to 2017. The results showed that XGBoost produced slightly better performance than RF, and the spatially continuous RHns model combined based on XGBoost yielded the coefficient of determination of 0.72 and a root-mean-square error of 10.61%. Spatiotemporal patterns of the estimated RHns agreed with in situ observations, reflecting the effect of topography on RHns. We expect that the proposed RHns model could be used in various environmental studies that require RHns under all sky conditions as input data
- …
