A Machine Learning approach to reconstruct cloudy affected vegetation indices imagery via data fusion from Sentinel-1 and Landsat 8

归一化差异植被指数 随机森林 遥感 植被(病理学) 合成孔径雷达 增强植被指数 传感器融合 环境科学 土地覆盖 多元统计 计算机科学 人工智能 机器学习 植被指数 气候变化 地质学 土地利用 工程类 医学 海洋学 土木工程 病理
作者
Erli Pinto dos Santos,Demétrius David da Silva,Cibele Hummel do Amaral,Elpídio Inácio Fernandes Filho,Rafael Luís Silva Dias
出处
期刊:Computers and Electronics in Agriculture [Elsevier BV]
卷期号:194: 106753-106753 被引量:28
标识
DOI:10.1016/j.compag.2022.106753
摘要

• A machine learning based method is proposed to fusion optical and radar images. • Radar vegetation observations were suitable to predict optical vegetation indices. • Random forest algorithm showed best performance in predicting vegetation indices. • Random forest models reconstructed vegetation indices images affected by clouds. A way to reconstruct optical sensor-derived images allowing cloud-free vegetation monitoring is proposed in this paper. The motivation is the influence that clouds have on optical remote sensing of tropical regions, which hinders Earth observation systems because their presence reduces imaging frequency. To circumvent that problem, a machine learning model-based integration methodology for the fusion of Landsat 8 and Sentinel-1 data is proposed herein. Sentinel-1 constellation has mounted Synthetic aperture radar (SAR) sensors are used because the imaging is not affected by clouds due to microwave spectrum characteristics. To study the problem and predict both the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI), three algorithms were selected: multivariate linear regression, multivariate adaptive regression splines, and random forest (RF). Two testing strategies were also chosen: k-Fold cross-validation for hyperparameter tuning of the model and holdout testing to assess the generalization ability of the model. The SAR covariables were employed to feed the algorithms, including selected SAR vegetation indices; in addition, environmental data, such as land use and land cover (LULC), the date, and position of the samples were used. The predictions from the NDVI and EVI produced good results, namely, similar Willmott’s agreement index (d) values that ranged from ∼0.64 to 0.96. The best-fitted model was the RF, which was used to reconstruct the NDVI images and produced good results that agreed well with the predictions (d index from 0.58 to 0.87) and spatial patterns. The results obtained show that the integration of radar and environmental covariables with optical vegetation indices can allow vegetation monitoring that is free of gaps due to clouds.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
碳烤小肥肠完成签到,获得积分10
刚刚
夌隺完成签到,获得积分10
刚刚
木卫三完成签到,获得积分10
1秒前
哈基米完成签到 ,获得积分20
1秒前
鱼饼完成签到 ,获得积分10
1秒前
合适怡完成签到,获得积分10
1秒前
夜已深完成签到,获得积分10
1秒前
安静的从安完成签到,获得积分10
2秒前
健忘的芷荷完成签到,获得积分10
2秒前
2秒前
Banbor2021完成签到,获得积分0
3秒前
hzhang完成签到,获得积分10
3秒前
3秒前
yummy完成签到,获得积分10
4秒前
SA发布了新的文献求助30
4秒前
KVBVB完成签到,获得积分10
4秒前
4秒前
奋斗的若云完成签到,获得积分10
4秒前
小悦悦完成签到 ,获得积分10
5秒前
5秒前
zsyzxb完成签到,获得积分10
5秒前
LI完成签到,获得积分10
6秒前
6秒前
Liar完成签到,获得积分10
6秒前
知123完成签到,获得积分10
6秒前
way完成签到,获得积分10
7秒前
小二郎应助gdh采纳,获得10
7秒前
lyp7028发布了新的文献求助10
7秒前
无辜访彤发布了新的文献求助10
8秒前
8秒前
英俊的铭应助miemie阳采纳,获得10
8秒前
一叶知秋完成签到,获得积分10
10秒前
胡杨完成签到,获得积分10
10秒前
思源应助刘宇采纳,获得10
10秒前
bind发布了新的文献求助10
10秒前
10秒前
zyj完成签到,获得积分10
11秒前
贺兰鸵鸟完成签到,获得积分10
11秒前
zwenng完成签到,获得积分10
11秒前
12秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968719
求助须知:如何正确求助?哪些是违规求助? 3513608
关于积分的说明 11168681
捐赠科研通 3248960
什么是DOI,文献DOI怎么找? 1794573
邀请新用户注册赠送积分活动 875194
科研通“疑难数据库(出版商)”最低求助积分说明 804716