Yu-Cheng Chen

The high intensity of urban development in recent years has replaced many natural surfaces with artificial objects. Buildings and roads have increased heat storage, which has become one of the leading causes of urban hyperthermia. In the past, studies on urban form and the thermal environment mainly used surface coverage analysis. However, surface classification cannot effectively consider three-dimensional urban information such as building height and density. Therefore, this study will use Local Climate Zone (LCZ) as a classification method to investigate urban form and temperature. LCZ is a classification method that explores the association between urban form and temperature. Since the classification process of LCZ is a supervised classification using satellite images, the results are subjectively influenced. Therefore, this project selects several representative zones, combines the LCZ classification with the types defined by each category, and conducts a questionnaire survey on 50 students with architecture and landscape planning backgrounds to compile the classification results of most people in each representative zone. The survey results were used for training, and the types of LCZs in the study site were summarized. The results showed that the accuracy of the objective classification results was 5.5% higher than that of the subjective classification. Increasing the number of training areas from 3 to 8 for each type also improved the accuracy by about 4.5%. In addition, this study analyzed the LCZ classification of buildings and landscapes in each region and the influence of temperature through the temperature data of the Meteorological Bureau in 2022. It was found that the average LCZ temperature in built-up areas could reach 32°C, while the average LCZ temperature in non-built-up areas was about 30.5°C in summer daytime. This study will serve as a reference for urban design to reduce the temperature for the potential of sustainable urban development.

High temperatures have become common in cities in Taiwan, and this phenomenon has spread to surrounding agricultural areas. Tainan, a city located in a tropical climate zone with agriculture as its primary development industry, is one of the cities considerably affected by the high temperature. High temperatures can reduce crop yields and even cause plant death, especially for vulnerable high-value crops, which are severely to microclimate conditions. Asparagus is a high-value crop that has long been cultivated in the Jiangjun District of Tainan. Recently, asparagus has been planted in greenhouses to protect against pests and natural disasters. However, the greenhouses can overheat. To identify the optimal growth environment for asparagus, this study applies vertical monitoring to record the temperature in the greenhouse and the soil moisture content of a control (canal irrigation) and an experimental (drip irrigation) group. When the surface layer of the soil exceeds 33°C, the tender stems of asparagus bloom readily, reducing its commercial value. Therefore, drip irrigation was conducted with cool water (26°C) to reduce soil temperature in summer and warm water (28°C) to increase soil temperature in winter. The study also recorded the growth of asparagus using daily yields measured by farmers during weighing and packing to understand the benefits of controlling the greenhouse microclimate. This study reports a correlation of 0.85 between asparagus yield and temperature and a correlation of 0.86 between asparagus yield and soil moisture content. The use of a drip irrigation system with a water temperature adjustment function not only saves up to 50% of water but also resulted in an average yield increase of 10% through maintaining stable soil moisture content and temperature. Therefore, the findings of this study can be applied to asparagus yields affected by high temperature and can solve the problems of poor quality in summer and low yield in winter.

Urban Heat Island (UHI) is an evident phenomenon in Taiwan, especially the capital Taipei city, owing to the highly developed with numerous high-rise buildings and the basin terrain. Due to the problem above, a method to estimate the thermal stress possibility based on the urban pattern is necessary. In recent years, machine learning and deep learning developed quickly and achieved in many fields like image recognition, machine translation, and predicting environmental characteristics. With the excellent development of machine learning and deep learning, a novel method for estimating the thermal stress possibility was presented in this work. In this study, the average temperature distribution in Taipei at 1 pm in August 2021 was calculated based on the information from measurement points of the high-density street-level air temperature observation network (HiSAN) and the Central Weather Bureau (CWB). And the thermal condition was classified into three classes: the low, medium, and high possibility of thermal stress based on the median, upper quartile, and top 90% of the data. Simultaneously, Taipei city was classified with Local Climate Zone (LCZ) based on the satellite image from Landsat 8. And this study also collected the terrain data to correct the effect of altitude on temperature. The LCZ map and terrain were resampled into 100m spatial resolution for the subsequent work. Artificial Neural Network (ANN) and Deep Neural Network (DNN) were used and compared this work’s performances for estimating the thermal stress possibilities in Taipei city. The LCZ map and terrain data were reshaped as the images with 64 pixels to quantize pattern features within the areas of 800m2 and inputted into the models for training and predicting. Both ANN and DNN models have the same learning rate and training epochs which were 0.001 and 500 epochs. After the training processes of the models, ANN and DNN models were able to estimate the possibility of thermal stress for each area by LCZ map and terrain data. The results of ANN and DNN models proved the feasibility of using algorithms of machine learning and computer vision to assess microclimate conditions. Also, the novel method presented in this work can help estimate the thermal stress possible for the areas without measurement points.

Due to the urban heat island effect becoming more evident in the cities in Taiwan, the urban climate has become an essential factor in urban development. Taiwan is located on the border of tropical and subtropical climate zones, the climate condition is hot and humid, and the city shows high-density development. The dense urban development has increased the heat storage capacity of the ground and buildings. However, if only the climate stations set by the Central Meteorological Bureau to observe the climate data are applied, the predicted results differ from the actual urban climate conditions due to the small number of these stations and the too far distance between them. Therefore, this study employs the local climate zone (LCZ), which can classify the land features by considering both land use and land cover, and can be freely generated from satellite images. The LCZ classification method can view the type of the city through the height and density of obstacles. This study also combines the urban canopy model (UCM) of the mesoscale climate prediction model and weather research and forecasts (WRF). This approach can calculate vertical and horizontal planes of the city, such as building volume, road width, the influence of streets and roofs, roof heat capacity, building wall heat capacity, etc., to predict the climatic conditions in different lands in the study area. Simultaneously, to understand the actual distribution of urban climate more accurately, this study used the microclimate measurement network built in the research area to produce pedestrian-level temperature distribution and compared the estimated results with the actual measured values for urban climate assessment. This study can understand the cause of urban heat islands and assist urban planners more appropriately formulate heat island mitigation strategies in different regions.

The climate in Taiwan is hot and humid, and urban show high-density development. The dense urban development has increased the heat storage of the ground and buildings. The compact arrangement of tall buildings causes the narrowness of the urban space to block the sky's view and hinders the relatively smooth airflow, which will cause problems such as poor ventilation in the city and cause high thermal risk in the city. In the past, when obtaining climate data, if only the climate stations set by the Central Meteorological Bureau were used, the distance between the stations was too far, and the coverage of the ground around the distribution area was almost the same, resulting in significant differences between the predicted results and the actual climate conditions. Therefore, this research established a microclimate measurement network to obtain climate data. For the urban environment information, the urban built environment data, such as digital surface model, and building information, were regulated data or required to purchase. Therefore, this study uses the Local Climate Zone (LCZ) which can consider land use and land cover simultaneously and can be freely produced by satellite images. The typology classification method can be used to view the city by the height and density of obstacles. LCZ can solve the inaccuracy of estimation caused by the mixed land-use in Taiwan and assign various types of related data from the scheme such as heat capacity, albedo, and roughness through classification results. This study herein applies LCZ combined with a mesoscale climate prediction model Weather Research and Forecasting (WRF) to predict the climate conditions within the study's scope and compare them with actual measured values. It can be used for urban climate assessment. The research results preliminarily show that by applying the LCZ classification and its corresponding factors to WRF with Multi-layer urban canopy model which can consider vertical surfaces such as building volume facades horizontal surfaces such as streets and roofs. The predicted temperature and actual temperature will be slightly underestimated, and it can be approximately between 1.5°C to 2.5°C in the urban area at night and 0.5°C to 1°C during the day. This phenomenon may be due to the relative ratio of buildings and road width in Taiwan, making the actual night. The heat dissipation effect is poor, and it is easy to cause heat accumulation in the urban area.