The department of a cloud-based application for estimating air temperature using satellite image and crowd-sourced weather data | |
| Author | Thannarot Kunlamai |
| Call Number | AIT Thesis no.RS-17-14 |
| Subject(s) | Clouds Remote sensing Temperature Remote-sensing images |
| Note | A thesis report submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Remote Sensing and Geographic Information Systems |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis;no. RS-17-14 |
| Abstract | Air temperature ( T a ) is one o f the most sensitive parameter of dynamical processes . Moreover, T a can be estimated from the relation between Land Surface T emperature (LST) satellite data product and surface air temperature from ground - based methodological stations . With t he availabi lity of crowd - source d personal weather observation devices , the reference d air temperature can be easily accessed via the I nternet. However, t he main problem of crowd - sourced data is the reliability of the data, it is needed to develop algorithm to filter outlier observation from crowd sources. Additionally , the technology of cloud computing is commonly used as a service infrastructure for processing task without installing software and it can help to reduce the time to develop web processing service. T he o verall objective of this study is the development of a cloud - based application for estimating T a . Firstly, a data collection system was developed to collect weather data from a distributed sensor network . Then, a suitable algorithm to filter weather da ta from crowd sources was applied for estimating air temperature with different land cover type and spatial distribution of weather station . T he crowdsourced weather data were requested by using Wundergroud weather API . In this study, we propose d the appro ach for estimating T a using the data at the same date and time the satellite passes the study area . We found that our approaches that are the estimating T a based on land cover type and based on spatial distribution give the better accuracy than the c onventional method that conducted with the data in one year period. And also by filtering the outlier observation from nearby area within 10 kilometers, we found the high difference value of RMSE was obtained around 1.00 °C when comparing with the estimati ng T a using all crowdsourced weather data without data filtering. According to the result s of comparing the performance between the standard weather stations which the small number of weather station and crowdsourced weather stations have been indicated that the number of weather station affected the accuracy of the estimated air temperature map. The estimating air temperature using crowdsourced weather data from 228 weather stations gives the lower RMSE than using the standard weather data from 10 ASOS stations with approximately 1.00 °C. The application was developed with JavaScript, Google Map API, Google Visualization API, and Google Earth Engine that used to retrieve and process geospatial data on Google’s infrastructure . The cloud - based application was configured to provide the air temperature information on the Internet and allow the user can export the estimated air temperature image in TIFF file through the web browser. The estimated air temperature data from this study can be as preliminary data for further analysis such as weather prediction and weather forecasting application. |
| Year | 2017 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis;no. RS-17-14 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Sarawut Ninsawat |
| Examination Committee(s) | Apichon Witayangkurnว Miyazaki, Hiroyuki |
| Scholarship Donor(s) | RTG Fellowship |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 2017 |