Multi-scale spatial and spectral feature fusion for soil carbon content prediction based on hyperspectral images

高光谱成像 比例(比率) 特征(语言学) 融合 碳纤维 内容(测量理论) 遥感 环境科学 空间生态学 土壤碳 土壤科学 模式识别(心理学) 计算机科学 人工智能 土壤水分 数学 生态学 地质学 地理 地图学 生物 数学分析 语言学 哲学 算法 复合数
作者
Xueying Li,Zongmin Li,Huimin Qiu,Guangyuan Chen,Pingping Fan,Yan Liu
出处
期刊:Ecological Indicators [Elsevier]
卷期号:160: 111843-111843 被引量:1
标识
DOI:10.1016/j.ecolind.2024.111843
摘要

Soil carbon content prediction based on hyperspectral images can achieve large-scale spatial measurement, which has the advantages of wide coverage and fast information collection, is more suitable for field data collection. However, the research on soil carbon content prediction based on hyperspectral images mainly focuses on feature extraction of spectral information, ignoring the spatial information, and cannot well reveal the intrinsic structural characteristics of data. Aiming at the lack of spatial features consideration in hyperspectral images, soil carbon content prediction methods based on multi-scale feature fusion are proposed by hyperspectral image. At the same time of extracting spectral features from hyperspectral images, the spatial information is used for the first time and a multi-scale spectral and spatial feature network (SpeSpaMN) is designed. In the SpeSpaMN, the multi-scale spectral feature network (SpeMN) is constructed to extract spectral features, the multi-scale spatial feature network (SpaMN) is constructed to extract spatial features. The two networks are fused by using the complementary relationship between different scale features to achieve soil carbon content prediction based on multi-scale feature fusion. The results showed that SpeSpaMN had the best results compared to other methods, followed by the method of SpeMN. The RPD of Inland, Aoshan Bay and Jiaozhou Bay samples based on SpeSpaMN were increased by 47.36%, 37.96% and 4.30% respectively. This paper can effectively solve the problem of the deep fusion of spatial and spectral features in the soil carbon content prediction by hyperspectral image, so as to improve the accuracy and stability of soil carbon content prediction.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
wangli应助冷语采纳,获得20
1秒前
1秒前
pcx完成签到,获得积分10
2秒前
柚子完成签到,获得积分10
2秒前
舒心砖头完成签到,获得积分10
2秒前
amateur发布了新的文献求助10
3秒前
坚强莺完成签到,获得积分10
3秒前
FashionBoy应助暴躁的初夏采纳,获得10
3秒前
5秒前
Yxian发布了新的文献求助10
5秒前
走走走发布了新的文献求助10
5秒前
Owen应助aaaaaa采纳,获得10
6秒前
公子浅言完成签到 ,获得积分10
7秒前
乐乐发布了新的文献求助10
8秒前
amateur完成签到,获得积分10
11秒前
12秒前
慕青应助妈妈生的顶针采纳,获得10
12秒前
12秒前
dktrrrr完成签到,获得积分10
13秒前
哟嚛完成签到,获得积分10
14秒前
14秒前
讴歌发布了新的文献求助10
15秒前
大方的舞仙完成签到 ,获得积分10
15秒前
9527发布了新的文献求助10
17秒前
hxl123完成签到,获得积分10
19秒前
19秒前
ldgsd发布了新的文献求助30
20秒前
20秒前
芋泥波波完成签到,获得积分10
20秒前
JZJ完成签到,获得积分10
20秒前
chu完成签到,获得积分10
20秒前
21秒前
xiao完成签到,获得积分10
22秒前
希望天下0贩的0应助123采纳,获得10
22秒前
去看海嘛应助asdfghjkl采纳,获得10
23秒前
fanfan完成签到,获得积分10
24秒前
9527完成签到,获得积分10
24秒前
打打应助hyn采纳,获得10
25秒前
香蕉觅云应助独特的高山采纳,获得10
25秒前
26秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
An Introduction to Geographical and Urban Economics: A Spiky World Book by Charles van Marrewijk, Harry Garretsen, and Steven Brakman 600
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3153496
求助须知:如何正确求助?哪些是违规求助? 2804706
关于积分的说明 7861097
捐赠科研通 2462651
什么是DOI,文献DOI怎么找? 1310893
科研通“疑难数据库(出版商)”最低求助积分说明 629416
版权声明 601809