基于MWatNet模型的河套灌区解放闸灌域灌溉水体提取
Extraction of Irrigation Water Body in Jiefangzha Irrigation Area of Hetao Irrigation District Based on MWatNet Model
张圣微 1韩永婷 2刘璐 3杨林 3雒萌 3方科迪 3章骞3
作者信息
- 1. 内蒙古农业大学水利与土木建筑工程学院,呼和浩特 010018;内蒙古自治区水资源保护与利用重点实验室,呼和浩特 010018
- 2. 内蒙古农业大学水利与土木建筑工程学院,呼和浩特 010018;黄河流域内蒙段水资源与水环境综合治理自治区协同创新中心,呼和浩特 010018
- 3. 内蒙古农业大学水利与土木建筑工程学院,呼和浩特 010018
- 折叠
摘要
为提高灌溉农田中灌溉水体的识别精度,以河套灌区解放闸灌域作为研究区,基于Sentinel-2遥感影像,结合灌区实际情况对地表水体提取模型(WatNet)进行改进,得到MWatNet模型并提取灌溉水体.采用总体精度(Overall accuracy,OA)、平均交并比(Mean intersection over union,MIoU)、F1值等水体提取精度指标进行综合评价.结果表明:改进后的地表水体提取模型(MWatNet)在解放闸灌域农田灌溉水体的提取上具有较好的识别精度,模型总体精度达到96％,平均交并比达到83％,F1值为80％,实地调研验证准确度为85.7％;对比原WatNet、水体语义分割模型(Deeplabv3_plus)和水体提取模型(Deepwatermapv2),MWatNet在灌溉水体提取的连结性、剔除道路和城镇干扰等方面,均表现出更好的效果和模型运行效率.利用该模型可以实现灌溉水体定量化表征,为灌溉用水调度提供了数据支撑.
Abstract
In order to improve the recognition accuracy of irrigation water bodies in irrigated farmland,the Jiefangzha Irrigation Area of Hetao Irrigation District was taken as the study area,and the surface water body extraction model(WatNet)was improved based on Sentinel-2 remote sensing images,combined with the actual situation of the irrigation area,to obtain the MWatNet model and extract irrigation water bodies.Overall accuracy(OA),mean intersection over union(MIoU),F1 value and other water body extraction accuracy indicators were used for comprehensive evaluation.The results showed that the improved surface water body extraction model(MWatNet)had good recognition accuracy in the extraction of farmland irrigation water bodies in Jiefangzha Irrigation Area,the overall accuracy of the model reached 96％,the mean interaction over union reached 83％,the F1 value was 80％,and the accuracy of the field research validation was 85.7％;comparing with the original WatNet,the semantic segmentation model of water bodies(Deeplabv3_plus),and the water body extraction model(Deepwatermapv2),MWatNet showed better results and model operation efficiency in terms of connectivity of irrigation water body extraction,and elimination of road and town interference.The quantitative characterization of irrigation water bodies can be achieved by using this model,which provided data support for irrigation water scheduling.
关键词
水体提取/灌溉农田/Sentinel-2影像/深度学习/河套灌区/MWatNet模型Key words
water body extraction/irrigated farmland/Sentinel-2 image/deep learning/Hetao Irrigation District/MWatNet model引用本文复制引用
基金项目
国家重点研发计划重点项目(2021YFC3201201)
内蒙古自治区科技成果转化项目(2020CG0054)
内蒙古自治区高等学校创新团队发展计划项目(NMGIRT2313)
"草原英才"创新团队项目()
出版年
2024
国家科技期刊平台
NSTL
万方数据