Predicting Abiotic Soil Characteristics Using Sentinel-2 at Nature-Management-Relevant Spatial Scales and Extents

TY - JOUR

T1 - Predicting Abiotic Soil Characteristics Using Sentinel-2 at Nature-Management-Relevant Spatial Scales and Extents

AU - Moeslund, Jesper Erenskjold

AU - Damgaard, Christian Frølund

N1 - Publisher Copyright: © 2024 by the authors.

PY - 2024/8

Y1 - 2024/8

N2 - Knowledge of local plant community characteristics is imperative for practical nature planning and management, and for understanding plant diversity and distribution drivers. Today, retrieving such data is only possible by fieldwork and is hence costly both in time and money. Here, we used nine bands from multispectral high-to-medium resolution (10–60 m) satellite data (Sentinel-2) and machine learning to predict local vegetation plot characteristics over a broad area (approx. 30,000 km2) in terms of plants’ preferences for soil moisture, soil fertility, and pH, mirroring the levels of the corresponding actual soil factors. These factors are believed to be among the most important for local plant community composition. Our results showed that there are clear links between the Sentinel-2 data and plants’ abiotic soil preferences, and using solely satellite data we achieved predictive powers between 26 and 59%, improving to around 70% when habitat information was included as a predictor. This shows that plants’ abiotic soil preferences can be detected quite well from space, but also that retrieving soil characteristics using satellites is complicated and that perfect detection of soil conditions using remote sensing—if at all possible—needs further methodological and data development.

AB - Knowledge of local plant community characteristics is imperative for practical nature planning and management, and for understanding plant diversity and distribution drivers. Today, retrieving such data is only possible by fieldwork and is hence costly both in time and money. Here, we used nine bands from multispectral high-to-medium resolution (10–60 m) satellite data (Sentinel-2) and machine learning to predict local vegetation plot characteristics over a broad area (approx. 30,000 km2) in terms of plants’ preferences for soil moisture, soil fertility, and pH, mirroring the levels of the corresponding actual soil factors. These factors are believed to be among the most important for local plant community composition. Our results showed that there are clear links between the Sentinel-2 data and plants’ abiotic soil preferences, and using solely satellite data we achieved predictive powers between 26 and 59%, improving to around 70% when habitat information was included as a predictor. This shows that plants’ abiotic soil preferences can be detected quite well from space, but also that retrieving soil characteristics using satellites is complicated and that perfect detection of soil conditions using remote sensing—if at all possible—needs further methodological and data development.

KW - habitat condition

KW - indicator values

KW - machine learning

KW - plant communities

KW - plant species

KW - remote sensing

KW - satellite data

UR - http://www.scopus.com/inward/record.url?scp=85202628725&partnerID=8YFLogxK

U2 - 10.3390/rs16163094

DO - 10.3390/rs16163094

M3 - Journal article

AN - SCOPUS:85202628725

SN - 2072-4292

VL - 16

JO - Remote Sensing

JF - Remote Sensing

IS - 16

M1 - 3094

ER -