Uncovering the rapid expansion of photovoltaic power plants in China from 2010 to 2022 using satellite data and deep learning

光伏系统 遥感 地理空间分析 中国 环境科学 自然地理学 气象学 地理 生态学 生物 考古
作者
Yuehong Chen,Jiayue Zhou,Yong Ge,Jinwei Dong
出处
期刊:Remote Sensing of Environment [Elsevier]
卷期号:305: 114100-114100 被引量:74
标识
DOI:10.1016/j.rse.2024.114100
摘要

China's rapid deployment of solar photovoltaic (PV) power plants has positioned it as the global leader in cumulative installed capacity. The expansion patterns of PV power plants in China play a crucial role in promoting PV diffusion in markets, shaping policies, and analyzing environmental and social impacts. However, the current geospatial datasets of PV power plants available for China cannot fully address these needs due to either missing installation dates or outdated information. Hence, this study develops a framework to extract the spatial extent and installation date of PV power plants from Sentinel-2 and Landsat data using deep learning and change detection techniques and uncover their expansion patterns in China. A geospatial dataset of PV polygons with installation dates in China from 2010 to 2022 is obtained with the F1-score of 96.08% for its spatial extent and the overall accuracy of 89.86% for its installation dates. We found that western China has a higher total PV area but a lower density of large-size PV power plants whereas eastern and central China have lower total PV areas but a higher density of small-size PV power plants. The area of PV power plants in China has over 600-fold increase from 5.86 km2 in 2010 to 3712.1 km2 in 2022 with the average annual growth of 285 km2 and western China has the highest annual growth proportion of 53%. The PV power plants in eastern and central China mainly established on croplands (24.6%) and the occupation of croplands presents a significant reduction of 48% from 2017 to 2022. In contrast, PV installations in western China, especially poverty-stricken areas, are primarily deployed on grasslands (28.3%) and unused lands (27.5%) and a declining pattern is observed in the occupation of grasslands. The up-to-date geospatial dataset of PV power plants and their expansion pattern analysis offer valuable insights into the understanding of PV development and its land occupation in both space and time, and thereby contribute to the policy-making of carbon mitigation for China.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI

祝大家在新的一年里科研腾飞
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
tangyuyi完成签到,获得积分10
刚刚
刚刚
lejunia发布了新的文献求助50
1秒前
liweivvvvv完成签到,获得积分10
2秒前
3秒前
CipherSage应助帅气书白采纳,获得10
3秒前
ChenXinde完成签到,获得积分10
5秒前
6秒前
8秒前
8秒前
9秒前
微笑荟完成签到 ,获得积分10
9秒前
陌上花开完成签到,获得积分0
10秒前
科研通AI6.2应助NEU_HMY采纳,获得10
10秒前
小熊天天学习完成签到 ,获得积分10
11秒前
11秒前
milly发布了新的文献求助10
12秒前
只喝怡宝发布了新的文献求助10
13秒前
13秒前
祖小凝发布了新的文献求助10
13秒前
15秒前
ZORROR发布了新的文献求助10
16秒前
CipherSage应助lejunia采纳,获得10
17秒前
17秒前
慕青应助lejunia采纳,获得10
17秒前
fanhaomeng发布了新的文献求助10
19秒前
只喝怡宝完成签到,获得积分20
20秒前
Ava应助ZORROR采纳,获得10
21秒前
篇篇高分发布了新的文献求助10
21秒前
小冉不熬夜完成签到 ,获得积分10
22秒前
22秒前
26秒前
小苹果汤完成签到,获得积分10
27秒前
杨程蛟完成签到,获得积分10
27秒前
27秒前
哈哈哈完成签到 ,获得积分10
28秒前
29秒前
30秒前
篇篇高分完成签到,获得积分10
30秒前
流星雨完成签到 ,获得积分10
31秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Les Mantodea de guyane 2500
Signals, Systems, and Signal Processing 510
Discrete-Time Signals and Systems 510
Driving under the influence: Epidemiology, etiology, prevention, policy, and treatment 500
生活在欺瞒的年代:傅树介政治斗争回忆录 260
A History of Rice in China 200
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 计算机科学 有机化学 物理 生物化学 纳米技术 复合材料 内科学 化学工程 人工智能 催化作用 遗传学 数学 基因 量子力学 物理化学
热门帖子
关注 科研通微信公众号,转发送积分 5874805
求助须知:如何正确求助?哪些是违规求助? 6510728
关于积分的说明 15675172
捐赠科研通 4992381
什么是DOI,文献DOI怎么找? 2691139
邀请新用户注册赠送积分活动 1633514
关于科研通互助平台的介绍 1591186