Air Temperature Prediction Research Articles

Assessing local heat stress and air quality with the use of remote sensing and pedestrian perception in urban microclimate simulations

Cities are increasingly confronted with multiple environmental and climatic stressors. Especially during heatwaves, street canyons are both producers and sufferers of air pollution and urban heat island (UHI) effects, with severe risks on public health. To better design mitigation measures, it is important to consider both the microclimate behaviors as well as the perceptions of the local population. Therefore, this study examined pedestrian perceptions and microclimate modelings to understand outdoor thermal comfort conditions and air pollution dispersion in the case study neighborhood of Dortmund Marten, Germany. A field survey with measurement points at two street canyons for climatic variables and questionnaires on subjective thermal comfort and air pollution was conducted on a hot day during the heatwave period in August 2020. As a cost-effective method for modeling input generation, we extracted spatial and spectral data like albedo, roof materials and tree locations out of remote sensing imageries. Finally, we compared the modeling results of the physiological equivalent temperature (PET) index, particulate matter concentrations and air temperatures with empirical field measurement data and the questionnaire responses. Results indicate that during hot summer days with light winds from the east, the north-south orientated street canyon with tree arrangements tends to act as a tunnel for particulate matter accumulation. Coincidently, pedestrians show less thermal discomfort than calculated PET values in that particular area during morning and daytime, which underlines the dichotomy of such places. On the other hand, the low rise east-west orientated street canyon shows higher PET votes than predicted by the model. However, particulate matter concentrations were considerably underestimated by the model, while air temperature predictions provided meaningful results. The proposed workflow shows the potential to accelerate future preparations of input data for microclimate modelings, while the results can enhance wind-sensitive planning procedures and heat stress resilience in mid-latitude urban neighborhoods.

Effect of heat mitigation strategies on thermal environment, thermal comfort, and walkability: A case study in Hong Kong

The effects of six heat mitigation strategies on thermal environment, thermal comfort, and walkability are evaluated. Thermal environment is simulated using a micro-scale computational fluid dynamic (CFD) model—ENVI-met. Thermal comfort is quantified with the Universal Thermal Climate Index (UTCI), which is linked to walkability through agent-based modeling (ABM). These integrated methods enable the quantitative assessment of how heat mitigation strategies used in urban planning affect human perceptions and behaviors. A typical high-density urban area in Hong Kong is used as a case study. Model validation reveals that the CFD model is partially accurate, performing the best in air temperature prediction. The results indicate that the type of infrastructure which causes the greatest reduction in air temperature does not necessarily lead to the biggest improvement in thermal comfort and walkability. Compared with the control, cool pavements reduce peak air temperature by 0.36 °C, and street trees reduce peak mean radiant temperature by 4.23 °C. Street trees also result in the lowest values of UTCI during the daytime, with a maximum UTCI reduction of 0.88 °C. In ABM simulations, street trees cause a reduction in perceived travel time (PTT) of up to 3 s per 100 m. However, the effects of other mitigation measures are marginal. Our findings suggest that although all heat mitigation strategies can be beneficial in improving the urban thermal environment, street trees are the most beneficial for improving thermal comfort and walkability.

A novel approach for solar greenhouse air temperature and heating load prediction based on Laplace transform

Solar greenhouses have provided favorable microclimates for improving and increasing crop production. As a significant factor of microclimates, greenhouse indoor air temperature has received extensive research attention in recent years. Although dynamic models were studied in diverse greenhouses, previous researches failed to consider the existing models' applicability, simplicity, and accurate boundary conditions for solar greenhouses. Hence, a dynamic thermal model based on Laplace transform was proposed for predicting solar greenhouse air temperature and heating load. The heat flux boundary conditions on interior surfaces of the greenhouse north wall and soil were revised by amending the solar fraction expressions with solar azimuth angle considered. The results indicated that the predicted air temperature was in good agreement with experimental values, and three evaluation indices of MAE, RMSE, and NRMSE were -1.250, 1.608, and 15.441%, respectively. Moreover, under three different indoor air conditions, the north wall and soil's heat transfer flux were analyzed, indicating that the north wall is the main loss part of the experimental greenhouse's opaque envelope. Besides, the results also demonstrated that the daily total heating load in Case 1 was larger than that in Case 3, which means different greenhouse air design temperature between day and night is more energy-saving in winter. Furthermore, the physical meaning of the air temperature solution expression and the limitations of this approach were also elaborated. The contribution of this study is to offer accurate temperature forecasting for solar greenhouses' heating, ventilation, and air conditioning applications in the future.

A Review of Neural Networks for Air Temperature Forecasting

The accurate forecast of air temperature plays an important role in water resources management, land–atmosphere interaction, and agriculture. However, it is difficult to accurately predict air temperature due to its non-linear and chaotic nature. Several deep learning techniques have been proposed over the last few decades to forecast air temperature. This study provides a comprehensive review of artificial neural network (ANN)-based approaches (such as recurrent neural network (RNN), long short-term memory (LSTM), etc.), which were used to forecast air temperature. The focus is on the works during 2005–2020. The review shows that the neural network models can be employed as promising tools to forecast air temperature. Although the ANN-based approaches have been utilized widely to predict air temperature due to their fast computing speed and ability to deal with complex problems, no consensus yet exists on the best existing method. Additionally, it is found that the ANN methods are mainly viable for short-term air temperature forecasting. Finally, some future directions and recommendations are presented.

Short time air temperature prediction using pattern approximate matching

Accurate prediction of outdoor air temperature is of great significance to improve the energy efficiency of HVAC system and even the whole building. The aim of this paper is to present the development and evaluation of a new algorithm based on pattern approximate matching for the prediction of outdoor air temperature using acquired historical data of five cities in China (Beijing, Harbin, Shanghai, Guangzhou and Kunming) representing different climatic regions. The optimum parameters of the algorithm for each city has been identified by its historical data. The efficiency of the prediction is validated by comparing predicted and measured outdoor air temperature. Furthermore, statistical metrics such as absolute mean error (AME), root mean square error (RMSE), and accuracy were used to evaluate the performance of the algorithm. These metrics confirm the algorithm proposed in this paper is suitable for all the five Chinese cities. All the work has been contacted using Python programming environment.

Permafrost thaw and ground settlement considering long-term climate impact in northern Alaska

Alaska’s North Slope is predicted to experience twice the warming expected globally. When summers are longer and winters are shortened, ground surface conditions in the Arctic are expected to change considerably. This is significant for Arctic Alaska, a region that supports surface infrastructure such as energy extraction and transport assets (pipelines), buildings, roadways, and bridges. Climatic change at the ground surface has been shown to impact soil layers beneath through the harmonic fluctuation of the active layer, and warmer air temperature can result in progressive permafrost thaw, leading to a deeper active layer. This study attempts to assess climate change based on the climate model data from the fifth phase of the Coupled Model Intercomparison Project and its impact on a permafrost environment in Northern Alaska. The predicted air temperature data are analyzed to evaluate how the freezing and thawing indices will change due to climate warming. A thermal model was developed that incorporated a ground surface condition defined by either undisturbed intact tundra or a gravel fill surface and applied climate model predicted air temperatures. Results indicate similar fluctuation in active layer thickness and values that fall within the range of minimum and maximum readings for the last quarter-century. It is found that the active layer thickness increases, with the amount depending on climate model predictions and ground surface conditions. These variations in active layer thickness are then analyzed by considering the near-surface frozen soil ice content. Analysis of results indicates that thaw strain is most significant in the near-surface layers, indicating that settlement would be concurrent with annual thaw penetration. Moreover, ice content is a major factor in the settlement prediction. This assessment methodology, after improvement, and the results can help enhance the resilience of the existing and future new infrastructure in a changing Arctic environment.

Air Temperature Prediction Using Different Datamining Approaches In Sulaymaniyah City In Iraq

Climate change has a historical impact at universal and local levels over the past era. Climate change is one of the greatest challenge issues in the globe for meteorological research. Air temperature estimation, in particular, has been measured as a significant feature in weather impression studies on industrial sectors, environmental, ecological, and agricultural. Accurately predicting air temperature guides to measure lifestyle, perform a key character for the government, industries, and public in development activities. In this paper, we investigate the use of various data mining approaches such as Support Vector Machine (SVM), Decision tree (DT), and Naïve Bayes for air temperature prediction within Sulaymaniyah City in Kurdistan, IRAQ. The metrological data is collected from the local Weather Forecast Department in the city within the range 2013 to 2018 inclusive. A dataset for the metrological data was developed and used to train the data mining algorithms. The proposed data mining algorithms were tested on the dataset to predict the air temperature and the performance of these algorithms were compared using standard performance metrics. Support vector machine has accomplished promising performance among using algorithms

Air temperature prediction using different machine learning models

Air temperature is an essential climatic component particularly in water resources management and other agro-hydrological/meteorological activities planning This paper examines the prediction capability of three machine learning models, least square support vector machine (LSSVM), group method and data handling neural network (GMDHNN) and classification and regression trees (CART) in air temperature forecasting using monthly temperature data of Astore and Gilgit climatic stations of Pakistan. The prediction capability of three machine learning models is evaluated using different time lags input combinations with help of root mean square error (RMSE), the mean absolute error (MAE) and coefficient of determination (R<sup>2</sup>).statistical indicators. The obtained results indicated that the LSSVM model is more accurate in temperature forecasting than GMDHNN and CART models. LSSVM significantly decreases the mean RMSE of the GMHNN and CART models by 1.47-3.12% and 20.01-25.12% for the Chakdara and Kalam Stations, respectively.

Contrasting Interannual Prediction between January and February Temperature in Southern China in the NCEP Climate Forecast System

AbstractThis study investigates the prediction of southern China surface air temperature (SAT) in January and February using hindcast and forecast dataset from the second version of the National Centers for Environmental Prediction Climate Forecast System, version 2 (NCEP CFSv2), for the period of 1983–2017. The observed January and February SAT in southern China is teleconnected with the Euro-Atlantic dipole (EAD) and the North Atlantic Oscillation (NAO), respectively. The February SAT is also teleconnected with El Niño–Southern Oscillation (ENSO) via the bridge with the Philippine Sea anticyclone. The CFSv2 better predicts southern China SAT in February than January, where the temporal correlation coefficients between the observed and predicted regional-mean SAT in February and January are +0.81 and +0.27 (+0.32 and +0.04), respectively, for the one-month (two month) ahead prediction. The better prediction in February coincides with 1) accurate responses of the Eurasian circulation and the Philippine Sea anticyclone to the NAO and the ENSO, respectively, and 2) a strong ENSO–NAO linkage. The poorer prediction in January is related to a stronger linkage of the predicted January SAT with the NAO rather than the EAD, as well as a weak ENSO–EAD linkage. These results advance our understanding of the subseasonal prediction of the winter temperature in southern China.

건물에너지 최적제어를 위한 실내온도 분포 예측 모델

Quantification of building energy performance is required for diagnosis, prediction, and evaluation of energy efficient use and performance improvement of buildings. Implementing a resistance capacity (RC) model, this study presents a hydrodynamic physical model that can predict the distribution of room temperatures with sensors of minimum quantity. The proposed prediction model could predict indoor thermal behavior very similarly, even though it did not link with other models or apply optimization techniques during the verification process. Under conditions not affected by thermodynamic parameters, the root mean square error (RMSE) range for predicting air temperature of other spaces was 0.115℃ to 0.357℃ with an average indoor air temperature of 0.132℃. Predictive models with simple input conditions developed in this study could be integrated with other various models and used for optimal control of building energy.

Prediction of 10-min, hourly, and daily atmospheric air temperature: comparison of LSTM, ANFIS-FCM, and ARMA

Prediction of atmospheric air temperature (AAT) time series is an important issue as it gives information to society and sustainability for future planning. In this study, a deep learning method, namely, long short-term memory (LSTM) network, based on one-step-ahead prediction approach was proposed to predict AAT using the actual time series data. For the proposed prediction method, a set of measurement data in 10-min, hourly, and daily intervals obtained from Mersin and Belen stations located in the Eastern Mediterranean Region of Turkey was used. Mean absolute percentage error (MAPE), root mean square error (RMSE), correlation coefficient (R), mean absolute error (MAE), and average bias were considered as evaluation criteria. According to the testing process, the RMSE, MAPE, MAE, R, and bias values for the 10-min interval AAT prediction were calculated as 0.35 °C, 1.40%, 0.25 °C, 0.995, and 0.074 °C, respectively. Considering the prediction results of the hourly AAT predication, the above statistical metrics with the same order were obtained as 0.61 °C, 1.85%, 0.43 °C, 0.945, and −0.013 °C. Concerning the daily AAT prediction results with LSTM, the above statistical metrics with the same order were computed as 1.33 °C, 3.27%, 0.99 °C, 0.97, and −0.116 °C. Compared to the hourly and daily AAT predictions, LSTM provided better accuracy results in predicting 10-min interval AAT. The prediction results from the three different time series data show that the prediction of AATs using LSTM can provide high accuracy results for short-term prediction using data with a long period time. On the other hand, adaptive neuro-fuzzy inference system with fuzzy C-means (ANFIS-FCM) method and autoregressive moving average (ARMA) model were also used to compare the results of LSTM method. Both LSTM and ANFIS-FCM network model showed high accuracy for the prediction of 10-min interval, hourly, and daily AAT data with RMSE values between 0.31 and 1.52 °C, while ARMA model failed to provide high accuracies for all predictions.

Prediction of vertical thermal stratification of large space buildings based on Block-Gebhart model: Case studies of three typical hybrid ventilation scenarios

Although nozzle air supply is considered to be dominant when creating the thermal environment of the occupied area in a large space building, natural ventilation and air infiltration can interact with nozzle jets, resulting in a complex air distribution inside the building. This study focuses on the prediction of indoor vertical temperature distribution in large space buildings under the coupling of multiple airflows. Based on the validated regional model, Block-Gebhart (B-G) model, three auxiliary models were introduced for three types of common building ventilation scenarios, namely nozzle air supply, natural ventilation, and air infiltration. The auxiliary models were combined with the basic model to predict the indoor thermal environment of large space buildings in three hybrid ventilation scenarios. Field measurements of the vertical air temperatures of these three buildings were carried out to verify the feasibility and accuracy of the composite model. The results showed that the average deviations of air temperature in the International Gymnastics Stadium, the Ecological Demonstration Building and the Engineering Training Plant were 0.85, 0.80, and 0.32 °C, respectively. The building with the minimum deviation was the training plant, because the prediction of air temperature of this building took into account both jet entrainment and air infiltration phenomenon, so that the description of its indoor airflow pattern was the most accurate. The composite model proposed in this paper extends the application of the B-G model in hybrid ventilation scenarios and supplements the present design system of air distribution in large space buildings.

Applying urban climate model in prediction mode\u2014evaluation of MUKLIMO_3 model performance for Austrian cities based on the summer period of 2019

Extreme heat events are natural hazards affecting many regions of the world. This study uses an example of the six largest cities in Austria to demonstrate the potential of urban climate model simulations applied in prediction mode providing detailed information on thermal conditions. For this purpose, the urban climate model MUKLIMO_3 of the German Meteorological Service (DWD) coupled with the hydrostatic numerical weather prediction model, ALARO, is used to simulate the development of the urban heat island (UHI) in Austrian cities for the summer period of 2019 with a horizontal resolution of 100 m. In addition to the evaluation of UHI predicting skills, other relevant variables, such as humidity and wind characteristics on hourly basis, are also analysed in this paper. Model evaluation confirmed that the MUKLIMO_3 microscale model had the capacity to simulate the main thermal spatiotemporal patterns in urban areas; however, a strong dependence on the input data from the mesoscale model was found. Our results showed large benefit in prediction of maximum air temperatures in urban areas, while the relative humidity predictions of MUKLIMO_3 appear to be much less plausible and show large variety of model prediction skills. Urban climate model simulations using real atmospheric conditions can facilitate better quantification and understanding of day-to-day intra-urban variations in microclimate as well as provide a basis for evaluation of the microclimate prediction skills of mesoscale numerical models with urban extensions.

Short-term air temperature prediction by adaptive neuro-fuzzy inference system (ANFIS) and long short-term memory (LSTM) network

Air Temperature (AT) is a crucial parameter for many disciplines such as hydrology, irrigation, ecology and agriculture. In this respect, accurate AT prediction is required for applications related to agricultural operations, energy generation, traveling, human and recreational activities. In this study, four different machine learning approaches such as Adaptive Neuro-Fuzzy Inference System (ANFIS) with Fuzzy C-Means (FCM), ANFIS with Subtractive Clustering (SC) and ANFIS with Grid Partition (GP) and Long Short-Term Memory (LSTM) neural network were used to make one-hour ahead and one-day ahead short-term AT predictions. Concerning the test site, the measured AT data were obtained from a solar power plant installed in the city of Tarsus, Turkey. Correlation coefficient (R), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used as quality metrics for prediction. Predicted values of the LSTM, ANFIS-FCM, ANFIS-SC and ANFIS-GP models were compared with the observed values by evaluating their prediction errors. According to the hourly AT prediction, the RMSE values in the testing process were found to be 0.644 (°C), 0.721 (°C), 0.722 (°C) and 0.830 (°C) for the LSTM, ANFIS-FCM, ANFIS-SC and ANFIS-GP models, respectively. On the other hand, the RMSE values of the corresponding methods for daily AT prediction were obtained as 1.360 (°C), 1.366 (°C), 1.405 (°C) and 1.905 (°C), respectively. The comparison of hourly and daily prediction results revealed that the LSTM neural network provided the highest accuracy results in both one-hour ahead and one-day ahead short-term AT predictions, and mainly presented higher performance than all ANFIS models.

The impact of time‐varying sea surface temperature on UK regional atmosphere forecasts

AbstractA new approach to improve the ocean surface boundary condition used in regional numerical weather prediction is proposed. Typically, regional atmosphere forecast systems assume a fixed sea surface temperature during a simulation. The study assesses the use of ocean temperature from an operational regional ocean model as an evolving lower boundary in a kilometre‐scale regional atmosphere configuration centred on the UK. Simulations of a winter and two five day duration summer case studies associated with anomalously warm temperatures are considered. The largest impact is found in summer, when a growing cold bias in mean temperature over land compared with observations is apparent when using a fixed global‐scale analysis lower boundary condition. The mean error is improved by 0.1 K when using a fixed temperature boundary condition from a kilometre‐scale regional ocean model initial condition. When using hourly surface temperature data from the same regional ocean model, the error is improved by 0.5 K for this case. Prediction of daytime maximum air temperature is also improved during the summer heat wave cases. A winter case study shows marginal improvement over the ocean and negligible changes over land. These results are confirmed in longer duration experiments using an hourly cycling regional forecast system with data assimilation for summer and winter periods. A systematic and statistically significant improvement of near‐surface temperature verification relative to the observations over land is demonstrated for both summer and winter using the new approach. This study supports future operational implementation of a time‐varying lower boundary for regional numerical weather prediction.

Air temperature forecasting using artificial neural network for Ararat valley

The air temperature is a critical factor in many societal challenges to protect human health and the environment. Moreover, a vital climatic parameter, the temperature has a direct impact on evaporation, frost, and snow melting. Temperature predictions are based mainly on numerical and statistical models. Sometimes it is a challenge to improve the weather forecast accuracy. The article aims to implement a weather prediction technique based on machine learning methods and approaches to improve the hourly air temperature prediction for up to 24 hours in the Ararat valley (Armenia). Due to intense heat and low relative humidity, the high temperatures and hot winds occur between 120 and 160 days per year in Ararat valley, as one of the aridest regions of Armenia. The approach utilizes the earth observation data received from several meteorological stations and the large satellite analysis-ready datasets at different frequencies and resolutions. The experiments have been conducted with multiple neural networks to forecast air temperatures for 24 hours that happened over the Ararat valley. The suggested model has 87.31% and 75.57% accuracies to predict the temperature for the next 3 and 24 hours, which is sufficient to be used alongside the current state-of-the-art techniques.

Analysis of extreme monthly and annual air temperatures variability using regression model in Mato Grosso do Sul, Brazil

Air temperature is a meteorological variable that influences the climate in the world. The availability of air temperature data is of concern in Brazil, particularly in the State of Mato Grosso do Sul (MS), since most weather stations are concentrated on the country's coast. Thus, the study aimed to develop models to estimate the average monthly and annual air temperatures (maximum and minimum) for the site of the State of MS. The linear multiple regression technique is adopted in this study. Temperature data from 1978 to 2018 were used, corresponding to 78 meteorological stations on the website of the State of MS. Geographical coordinates (latitude, longitude and altitude) were used as predictor variables for the models, and monthly and annual extreme temperatures (Tmax, Tmin) models were fitted. The regression models used in the study were statistically tested (α ≤ 0.01). The models of mean annual Tmin and mean annual Tmax obtained adjusted determination coefficients (R2adj) of 81.2% and 74.9%, respectively. The monthly average temperature models showed adjusted coefficients of determination between 0.69 and 0.90 for Tmax and from 0.71 to 0.86 for Tmin. Another method used to validate our results, the digital elevation model for the State of MS, obtained through a Shuttle Radar Topography Mission radar image. The obtained results fitted well with these of the annual and monthly models for extreme temperatures. The temperature models used in the study are duly suitable to predict air temperature in all sites in the State of MS.

The change in the probability of aviation accidents “Collision of an aircraft with a bird” in accordance with of a change in the temperature cycle

This paper considers the possibility of predicting the most frequent aviation event “Collision of an aircraft with a bird”, depending on the seasonality near the airfield. A model for determining the probability of this event is proposed, where the “time of year” is identified by the predicted air temperature near the airfield in question and the problem of determining the accumulated probability is solved. We consider the first approximation in which events are assumed to be independent (these are complex ecological and ornithological conditions and flaws of airfield’s ornithological support). Due to the first approximation of independence, the paper provides a possible way to determine the probability of the event “Collision of an aircraft with a bird”. This method (in the form of a formula) determines the probability of intersection of events caused by hazard factors. The result of the simulation is the probability of long-term forecasting of the probability of an aviation incident due to an aircraft collision.

Effect of melt ponds fraction on sea ice anomalies in the Arctic Ocean

We used deep learning networks to establish a relationship model among MODIS daily surface reflectance product (MOD09GA) and Arctic melt ponds fraction (MPF), ice fraction (IF), and open water fraction (OWF). We applied this model to MODIS 8-day surface reflectance (MOD09A1) to derive Arctic 8-day MPF and SIF (SIF as the sum of IF and MPF). The results demonstrate that our model improved MPF estimation accuracy to an RMSE of 3.7%, compared with previous models. The characteristics of MPF spatiotemporal changes seen in early summer (May-July) indicate that MPF increased first from May-June, reaching its peak around early July, and then decreased. In addition, early summer MPF was significantly negatively correlated with sea ice extent (SIE) in September. We also found that early summer MPF caused sea ice in the Beaufort Sea, the Chukchi Sea, and the East Siberian Sea to move to warm water. Moreover, the movement of sea ice from the marginal sea to the center of the Arctic was shown to be conducive to the reduction of SIE in September. Early summer MPF was also related to Arctic oscillation (AO) during June to July, and significantly positively related to air temperature in the East Siberian and Chukchi Seas in September. As a consequence, these areas produced more open water and absorbed more heat, reducing the extent of sea ice in September, while increasing their air temperatures. The results also show that early summer MPF has a high negative correlation with air temperature in northern China, and MPF can be used to predict air temperature in northern China. These new findings should be investigated in future studies with additional data collection and field observations.

Machine Learning-Based Microclimate Model for Indoor Air Temperature and Relative Humidity Prediction in a Swine Building.

Simple SummaryIndoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables. Among other livestock animals, pigs are more sensitive to environmental equilibrium; a lack of favorable environment in barns affects the productivity parameters such as voluntary feed intake, feed conversion, heat stress, etc. Machine learning (ML) based prediction models are utilized for solving various nonlinear problems in the current decade. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. Typically, most of the available IAT and IRH models are limited to feed the animal biological data as the input. Since the biological factors of the internal animals are challenging to acquire, this study used accessible factors such as external environmental data to simulate the models. Three different input datasets named S1 (weather station parameters), S2 (weather station parameters and indoor attributes), and S3 (Highly correlated values) were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available.Indoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables; still, potential contributors that influence the homeostasis of livestock animals reared in closed barns. Further, predicting IAT and IRH encourages farmers to think ahead actively and to prepare the optimum solutions. Therefore, the primary objective of the current literature is to build and investigate extensive performance analysis between popular ML models in practice used for IAT and IRH predictions. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. This study used accessible factors such as external environmental data to simulate the models. In addition, three different input datasets named S1, S2, and S3 were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction among other models particularly with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available. Overall, the current study demonstrates a better model among other models to predict IAT and IRH of a naturally ventilated swine building containing animals with fewer input attributes.