Mapping Invasive Tamarisk (Tamarix): A Comparison of Single-Scene and Time-Series Analyses of Remotely Sensed Data

Abstract

Abstract:In this study, we tested the Maximum Entropy model (Maxent) for its application and performance in remotely sensing invasive Tamarix sp. Six Landsat 7 ETM+ satellite scenes and a suite of vegetation indices at different times of the growing season were selected for our study area along the Arkansas River in Colorado. Satellite scenes were selected for April, May, June, August, September, and October and tested in single-scene and time-series analyses. The best model was a time-series analysis fit with all spectral variables, which had an AUC = 0.96, overall accuracy = 0.90, and Kappa = 0.79. The top predictor variables were June tasselled cap wetness, September tasselled cap wetness, and October band 3. A second time-series analysis, where the variables that were highly correlated and demonstrated low predictive strengths were removed, was the second best model. The third best model was the October single-scene analysis. Our results may prove to be an effective approach for mapping Tamarix sp., which has been a challenge for resource managers. Of equal importance is the positive performance of the Maxent model in handling remotely sensed datasets.

Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier

“…Some of the non-native invasive species frequently distinguished and mapped in the USA include saltcedar (Tamarix spp.) [33,52,58,59], leafy spurge (Euphorbia esula L.) [51,56,57], spotted knapweed (Centaurea maculosa Sam.) [32,48,53] and yellow starthistle (Centaurea solstitialis) [50,54,55].…”

A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems

“…This provides maximum entropy while avoiding assumptions on the unknown, hence the name of the classifier. MaxEnt was proposed to estimate geographic species distribution and potential habitat [56], to classify vegetation from remote sensing images [65], and groundwater potential mapping [66]. In our study, MaxEnt was applied with default parameter values in GEE as follows: weight for L1 regularization set to 0, weight for L2 regularization set to 0.00001, epsilon set to 0.00001, minimum number of iterations set to 0, and maximum number of iterations set to 100.…”

Integrating local pastoral knowledge, participatory mapping, and species distribution modeling for risk assessment of invasive rubber vine (Cryptostegia grandiflora) in Ethiopia’s Afar region

“…Within SAHM we used the Maxent statistical software package version 3.3.3k to train the model (Phillips et al 2006). This modeling approach is a general-purpose machine learning method that models species distributions from presence-only species occurrence records and has high accuracy in predicting plant distributions (Evangelista et al 2009, Elith et al 2011. The Maxent modeling output creates a surface with a continuous habitat suitability gradient with values ranging from 0 (least suitable or dissimilar) to 1 (most suitable or most similar to cells with occurrence points) and provides a calculation of the percent contribution of the different environmental variables used in the model.…”