{"title":"PyGRF:改进的 Python 地理随机森林模型及公共卫生和自然灾害案例研究","authors":"Kai Sun, Ryan Zhenqi Zhou, Jiyeon Kim, Yingjie Hu","doi":"10.1111/tgis.13248","DOIUrl":null,"url":null,"abstract":"Geographical random forest (GRF) is a recently developed and spatially explicit machine learning model. With the ability to provide more accurate predictions and local interpretations, GRF has already been used in many studies. The current GRF model, however, has limitations in its determination of the local model weight and bandwidth hyperparameters, potentially insufficient numbers of local training samples, and sometimes high local prediction errors. Also, implemented as an R package, GRF currently does not have a Python version which limits its adoption among machine learning practitioners who prefer Python. This work addresses these limitations by introducing theory‐informed hyperparameter determination, local training sample expansion, and spatially weighted local prediction. We also develop a Python‐based GRF model and package, PyGRF, to facilitate the use of the model. We evaluate the performance of PyGRF on an example dataset and further demonstrate its use in two case studies in public health and natural disasters.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"30 1","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"PyGRF: An Improved Python Geographical Random Forest Model and Case Studies in Public Health and Natural Disasters\",\"authors\":\"Kai Sun, Ryan Zhenqi Zhou, Jiyeon Kim, Yingjie Hu\",\"doi\":\"10.1111/tgis.13248\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Geographical random forest (GRF) is a recently developed and spatially explicit machine learning model. With the ability to provide more accurate predictions and local interpretations, GRF has already been used in many studies. The current GRF model, however, has limitations in its determination of the local model weight and bandwidth hyperparameters, potentially insufficient numbers of local training samples, and sometimes high local prediction errors. Also, implemented as an R package, GRF currently does not have a Python version which limits its adoption among machine learning practitioners who prefer Python. This work addresses these limitations by introducing theory‐informed hyperparameter determination, local training sample expansion, and spatially weighted local prediction. We also develop a Python‐based GRF model and package, PyGRF, to facilitate the use of the model. We evaluate the performance of PyGRF on an example dataset and further demonstrate its use in two case studies in public health and natural disasters.\",\"PeriodicalId\":47842,\"journal\":{\"name\":\"Transactions in GIS\",\"volume\":\"30 1\",\"pages\":\"\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transactions in GIS\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1111/tgis.13248\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GEOGRAPHY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions in GIS","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1111/tgis.13248","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOGRAPHY","Score":null,"Total":0}
PyGRF: An Improved Python Geographical Random Forest Model and Case Studies in Public Health and Natural Disasters
Geographical random forest (GRF) is a recently developed and spatially explicit machine learning model. With the ability to provide more accurate predictions and local interpretations, GRF has already been used in many studies. The current GRF model, however, has limitations in its determination of the local model weight and bandwidth hyperparameters, potentially insufficient numbers of local training samples, and sometimes high local prediction errors. Also, implemented as an R package, GRF currently does not have a Python version which limits its adoption among machine learning practitioners who prefer Python. This work addresses these limitations by introducing theory‐informed hyperparameter determination, local training sample expansion, and spatially weighted local prediction. We also develop a Python‐based GRF model and package, PyGRF, to facilitate the use of the model. We evaluate the performance of PyGRF on an example dataset and further demonstrate its use in two case studies in public health and natural disasters.
期刊介绍:
Transactions in GIS is an international journal which provides a forum for high quality, original research articles, review articles, short notes and book reviews that focus on: - practical and theoretical issues influencing the development of GIS - the collection, analysis, modelling, interpretation and display of spatial data within GIS - the connections between GIS and related technologies - new GIS applications which help to solve problems affecting the natural or built environments, or business