Home › Botany › Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling (SAHM)
Botany JoVE (Open Access) Citable · DOI

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling (SAHM)

DOI: 10.3791/54578-v
What you'll learn
  • ✓ Apply remote sensing data to invasive species distribution modeling using SAHM software
  • ✓ Construct ensemble predictive models for landscape-scale species occurrence mapping
  • ✓ Validate species distribution predictions through field surveys and accuracy assessment
Protocol

Biopharma Insights We demonstrate the utility of remotely sensed data and the newly developed Software for Assisted Habitat Modeling (SAHM) in predicting invasive species occurrence on the landscape. An ensemble of predictive models produced highly accurate maps of tamarisk (Tamarix spp.) invasion in Southeastern Colorado, USA when assessed with subsequent field validations.

Difficulty
advanced
Total time
~3–6 months (data acquisition, model training, field validation)

Steps

1
Understand remote sensing and species distribution modeling foundations

Review the ecological and methodological rationale for integrating remotely sensed environmental data with habitat suitability models to predict invasive species presence across landscapes.

▶ 00:22
2
Prepare data and configure SAHM predictive modeling workflow

Assemble remotely sensed environmental layers and species occurrence data, then configure the SAHM software to build an ensemble of predictive models for tamarisk distribution.

▶ 03:38
3
Generate and interpret landscape-scale distribution maps

Produce habitat suitability maps from the ensemble model output and examine the spatial predictions of invasive species occurrence across the study region.

▶ 10:30
4
Validate model predictions through field surveys

Compare model-predicted distributions to subsequent field validation data to assess mapping accuracy and model performance across the landscape.

▶ 11:26
💬 Comments coming soon