Using machine learning method to predict food waste in catering industry under high resolution: a case in Dongguan

IF 2.7 4区环境科学与生态学 Q3 ENVIRONMENTAL SCIENCES

Journal of Material Cycles and Waste Management Pub Date : 2023-05-20 DOI:10.1007/s10163-023-01706-8

Jiehong Tang, Yuting Tang, Yupeng Liu, Hanchen Su, Yuxuan Zhang, Ziwei Sun, Xiaoqian Ma

{"title":"Using machine learning method to predict food waste in catering industry under high resolution: a case in Dongguan","authors":"Jiehong Tang, Yuting Tang, Yupeng Liu, Hanchen Su, Yuxuan Zhang, Ziwei Sun, Xiaoqian Ma","doi":"10.1007/s10163-023-01706-8","DOIUrl":null,"url":null,"abstract":"<div><p>\nWaste classification is comprehensively carried out in China as an important national-level policy, and the large amount and the wide range of food waste generation (FWG) cause problems in the collection, transportation, and treatment. This study has conducted the prediction of FWG from the catering industry under high resolution, and provided suggestions and insights for food waste management and treatment. Taking Dongguan as an example, a Back Propagation Network (BPN) model is used to predict FWG under different operation data, and based on the acquired theoretical FWG numerical distribution, the intervals used to divide FWG values are determined. Then a Random Forest (RF) model is applied to predict the FWG intervals of the restaurants in the Point of Interest (POI) data. FWG of 96,303 restaurants is predicted, and the predicted FWG from the catering industry is about 3,106 t per day. Variation of FWG in different categories of restaurants, the material flow of FWG at the restaurant level, patterns of FWG at the restaurant level, and spatial patterns of FWG at the city level are also investigated. Suggestions for improvement of food waste collection standard and source reduction of FWG, and insights into food waste collection and distributed treatment system are raised.</p><h3>Graphical abstract</h3>\n <figure><div><div><div><picture><source><img></source></picture></div></div></div></figure>\n </div>","PeriodicalId":643,"journal":{"name":"Journal of Material Cycles and Waste Management","volume":"25 4","pages":"2442 - 2456"},"PeriodicalIF":2.7000,"publicationDate":"2023-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10163-023-01706-8.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Material Cycles and Waste Management","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s10163-023-01706-8","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

Waste classification is comprehensively carried out in China as an important national-level policy, and the large amount and the wide range of food waste generation (FWG) cause problems in the collection, transportation, and treatment. This study has conducted the prediction of FWG from the catering industry under high resolution, and provided suggestions and insights for food waste management and treatment. Taking Dongguan as an example, a Back Propagation Network (BPN) model is used to predict FWG under different operation data, and based on the acquired theoretical FWG numerical distribution, the intervals used to divide FWG values are determined. Then a Random Forest (RF) model is applied to predict the FWG intervals of the restaurants in the Point of Interest (POI) data. FWG of 96,303 restaurants is predicted, and the predicted FWG from the catering industry is about 3,106 t per day. Variation of FWG in different categories of restaurants, the material flow of FWG at the restaurant level, patterns of FWG at the restaurant level, and spatial patterns of FWG at the city level are also investigated. Suggestions for improvement of food waste collection standard and source reduction of FWG, and insights into food waste collection and distributed treatment system are raised.

Graphical abstract

查看原文本刊更多论文

基于机器学习方法的高分辨率餐饮业食物浪费预测——以东莞为例

垃圾分类作为一项重要的国家级政策在中国全面推行，食物垃圾产生量大、范围广，在收集、运输、处理等方面都存在问题。本研究对餐饮行业在高分辨率下的FWG进行了预测，为餐厨垃圾的管理和处理提供了建议和见解。以东莞为例，利用反向传播网络(BPN)模型对不同运行数据下的FWG进行预测，并根据获得的理论FWG数值分布，确定划分FWG值的区间。然后应用随机森林(RF)模型预测兴趣点(POI)数据中餐馆的FWG区间。预测96303家餐厅的FWG，餐饮业的FWG预计约为3106吨/天。研究了不同类型餐厅FWG的变化、餐厅层面FWG的物质流动、餐厅层面FWG的格局以及城市层面FWG的空间格局。提出了提高食物垃圾收集标准和减少FWG来源的建议，以及对食物垃圾收集和分布式处理系统的见解。图形抽象

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Material Cycles and Waste Management 环境科学-环境科学

CiteScore

5.30

自引率

16.10%

发文量

205

审稿时长

4.8 months

期刊介绍： The Journal of Material Cycles and Waste Management has a twofold focus: research in technical, political, and environmental problems of material cycles and waste management; and information that contributes to the development of an interdisciplinary science of material cycles and waste management. Its aim is to develop solutions and prescriptions for material cycles. The journal publishes original articles, reviews, and invited papers from a wide range of disciplines related to material cycles and waste management. The journal is published in cooperation with the Japan Society of Material Cycles and Waste Management (JSMCWM) and the Korea Society of Waste Management (KSWM).