High-Resolution Estimation of Monthly Air Temperature from Joint Modeling of In Situ Measurements and Gridded Temperature Data

Wilson, Bradley; Porter, Jeremy R.; Kearns, Edward; Hoffman, Jeremy S.; Shu, Evelyn; Lai, Kelvin; Bauer, Mark; Pope, Mariah

doi:10.3390/cli10030047

Cited by 10 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 A, where the k values are generally the highest. This is potentially driven by the tendency for anomalously large, yet rare, high-temperature extremes occurring in the blue-clustered region (that is sometimes referred to as the “extreme heat belt” 64 , which hosted the 1995 heat wave in Chicago, Illinois 65 , 66 , for example).…”

Section: Discussionmentioning

confidence: 99%

Exponential increases in high-temperature extremes in North America

Davariashtiyani,

Taherkhani,

Fattahpour

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Global warming in the 21st century will alter the frequency of extreme climatic events, such as high-temperature anomalies and “heat waves”. Observations of extreme high temperatures during recent decades have detected upward trends in their frequency of occurrence, and recent state-of-the-art Global Climate Models (GCMs), e.g., Climate Model Intercomparison Projects (CMIPs), notably CMIP5 and CMIP6, have predicted acceleration of temperature trends and high-temperature events by 2100 under projected greenhouse-gas emission scenarios. Hence, the 21st century is expected to experience substantial shifts in the occurrence of extreme events, where present-day, extreme-but-rare high-temperature events will become common during the summer months. The increasing frequency of extreme heat may affect the health and resiliency of social, biological, and infrastructure systems in many regions worldwide, underscoring the need for accurate and reliable long-term assessments of climatic change across global and regional scales. So far, many investigations of high-temperature extremes have been carried out under end-point scenarios, e.g., by comparing GCM-projected changes in the frequency of high-temperature extremes expected in the late 21st century to the late 20th century. In this study, we use extreme value theory and decades of observations of high-temperature extremes at thousands of meteorological stations across North America to investigate continuous shifts in the frequency of extreme high-temperature events due to projected local warming trends. We find that the odds of exceedance of 50-year extreme high-temperature events increases exponentially with increases in mean local temperature. At a majority of the stations studied here, a local mean temperature increase of 0.5–1 $$^{\circ }$$ ∘ C can double the odds of exceedance of 50-year extreme high-temperature events. Based on time-dependent temperature projections, the odds of exceedance of 50-year extreme high-temperature events doubles approximately every 20 years (or sooner) for $$\sim $$ ∼ 96% of the stations. Moreover, we find that, for $$\sim $$ ∼ 80% of the stations in North America, investigated here, the 50-year extreme high-temperature events will be exceeded annually before 2100.

show abstract

Section: Discussionmentioning

confidence: 99%

Exponential increases in high-temperature extremes in North America

Davariashtiyani,

Taherkhani,

Fattahpour

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…By doing so, the dataset is very precise in the local sites. A few researchers localized dataset points by combining sensors and satellite imagery [43,44], which may be quite complicated in real applications. An integrated database was created by combining remote sensing data and data collected by ground weather stations.…”

Section: Introductionmentioning

confidence: 99%

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

Tran,

Senkerik,

et al. 2023

mendel

View full text Add to dashboard Cite

This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.

show abstract

“…The urban heat island effect, land-atmosphere energy exchanges, and global climate change all benefit from accurate daily mean LST estimates sensors may deliver up to four instantaneous LSTs from across the world in a single day. However, many studies, such as those on climate change and hydrology, require daily mean LSTs rather than instantaneous values [13,14]. Based on a long-term MODIS series in the agricultural pastoral ecotone of northern China (2003-2020), Wei et al2021 evaluated the spatial, temporal, and trend aspects of LST on an annual and seasonal timeframe.…”

Section: Introductionmentioning

confidence: 99%

Integrated Approach for Land Surface Temperature Assessment in Different Topography of Iraq

Jabal¹,

Khayyun²,

Alwan³

2022

ETJ

View full text Add to dashboard Cite

 Analysis of Land Surface Temperature (LST) from ground weather stations in Iraq for various terrains.  Analysis of the maximum, minimum, and mean LST as long-term series from remote sensing output data (2000 to 2020).  Statistical Analysis (RMSE, NSE, R 2 , and Parson Correlation Coefficient) have been used to evaluate Tmin, Tmax, and Tmean between ground weather stations and MOD11C3 products. Land Surface Temperature (LST) is a critical parameter for water resources and hydrology investigation. Weather ground stations provide a continuous dataset on the LST. However, some stations rely on discrete events data, which shows limited capabilities to monitor diurnal and annual changes in LST. Remote Sensing technology provided much valid information by using Moderate Resolution Imaging Spectroradiometer (MODIS) to cover LST variations in Iraq. This study aims to analyze LST variation based on MOD11C3 Data with weather ground measurements stations for the different topography periods between 2000-2020. Different statistical parameters were used to validate LST results, including RSME; NSE; R 2 , and Parson Correlation. The results indicate agreement between MODIS and ground measurement stations during the winter season. The values ranged: RSME (close to zero); NSE (0 to 1); R 2 (between 0.5 and 1), and Parson Correlation (between 0.51 to 1).In spring, the values ranged: R 2 (between 0.5 and 1) and Parson Correlation (between 0.51 to 1). As the temperature rises during seasonal changes, the congruence in the four statistical indicators begins to decline dramatically. However, Baghdad, Basra, and Mosul stations still appear in good agreement, which is the validity of the data issued by MOD11C3. The finding presented in this research shows that the results of the LST by MOD11C3 are in good agreement and acceptable despite in various topographies of the ground stations.

show abstract

High-Resolution Estimation of Monthly Air Temperature from Joint Modeling of In Situ Measurements and Gridded Temperature Data

Cited by 10 publications

References 56 publications

Exponential increases in high-temperature extremes in North America

Exponential increases in high-temperature extremes in North America

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

Integrated Approach for Land Surface Temperature Assessment in Different Topography of Iraq

Contact Info

Product

Resources

About