| 摘要: |
| 园林绿化垃圾资源化循环利用的基础是处理设施体
系建设。以武汉市中心城区为例，分别对园林绿化垃圾空间分
布与处理设施选址进行研究。针对前者，基于高清卫片、街景
影像、行道树空间点位等大数据，利用机器学习中的分类(卷
积神经网络)、聚类(K均值聚类)和回归预测(多项式回归、随
机森林)等模型，实现对现状及规划地区的日常和峰值园林绿
化垃圾产生量的合理测算；针对后者，采用车辆路径问题类算
法中的自适应大邻域搜索算法，带入距离最近、运输周转量最
少、有限时间窗口和有限设施容量等限定条件，对组团收集
点、就近消纳站、综合处理厂和集中转运站4类设施及有关线
路进行智能选址。根据结果，预测研究区域内日常园林绿化垃
圾产生量为32.71 万t/年，峰值产生量为7 万t，与同等级城
市情况类似。建议布局200处组团收集点、50个就近消纳站、
4处综合处理厂和14个集中转运站，以提升园林绿化垃圾收集
清运效率，实现区域“产-收”平衡。 |
| 关键词: 风景园林 园林绿化垃圾 空间分布 处理设施选
址 机器学习 车辆路径问题 武汉市 |
| DOI：10.19775/j.cla.2024.07.0059 |
| 投稿时间：2023-07-12修订日期：2023-12-15 |
| 基金项目:国家自然科学基金重点课题(51978535) |
|
| Research on Spatial Distribution Prediction andTreatment Facility Location of Greenery WasteBased on Machine Learning and VRP Models: ACase Study of Wuhan City |
| ZHENG Duanya,ZHOU Xingyu,JI Donglan,DAI Shi,YOU Bixi |
| Abstract: |
| The system of landscaping waste treatment facilities
is the fundamental link for its resource utilization and recycling.
The research takes Wuhan as an example to study the spatial
distribution of greenery waste and the location of treatment facilities.
For the former, based on big data such as high-definition satellite
pictures, street view images, street tree spatial points, etc., and
using classification (convolutional neural network), clustering
(K-means clustering), regression prediction (polynomial regression),
the reasonable calculation of daily and peak greenery waste
volumes in current and planning areas is realized. For the latter,
the research adopts ALNS algorithm in vehicle routing problems,
which incorporates constraints such as closest distance, minimum
transportation turnover, limited time window, and limited facility
capacity. It intelligently selects four types of facilities, including
cluster collection points, nearby consumption stations, comprehensive
processing plants, and centralized transfer stations, as well as related
lines. The results show that the daily output of landscaping waste in
the study area is 327,100 tons/year, with a peak output of 70,000 tons,
similar to the situation in cities of the same level. It is recommended
to layout 200 cluster collection points, 50 nearby consumption
stations, 4 comprehensive treatment plants, and 14 centralized
transfer stations to improve collection and transportation efficiency
and achieve regional "production income" balance. |
| Key words: landscape architecture greenery waste spatial
distribution site selection of treatment facilities machine learning vehicle routing problem (VRP) Wuhan City |
