Stefan Peters

Dr. Stefan Peters

STEM, University of South Australia, Adelaide, South Australia, Australia
orcid

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 July 2023 in Land
Verified
Journal Article
Open access
PDF file
Tesfa Gebrie AndualemTesfa Gebrie Andualem
Tesfa Gebrie Andualem
GHGUNA HEWA
GUNA HEWA
BMBaden Myers
Baden Myers
SPStefan Peters
Stefan Peters
John BolandJohn Boland
John Boland
Soil erosion and sediment transport have significant consequences, including decreased agricultural production, water quality degradation, and modification to stream channels. Understanding these processes and their interactions with contributing factors is crucial for assessing the environmental impacts of erosion. The primary objective of this review is to identify a suitable soil erosion and sediment transport model for catchment-scale application. The study considers various model selection processes, including model capability and the spatial and temporal domains for assessing spatiotemporal distributions. The review acknowledges the limitations, uncertainties, and unrealistic assumptions associated with soil erosion and sediment transport models. Models are usually developed with a particular objective, which demands an assessment of capabilities, spatial, and temporal applicability, and catchment-scale applicability. Distributed models are often preferred for catchment-scale applications, as they can adequately account for spatial variations in erosion potential and sediment yield, aiding in the evaluation of erosion-contributing elements and planning erosion control measures. Based on the findings of this study, the authors encourage utilizing models (such as Soil and Water Assessment Tool (SWAT) or Automated Geospatial Watershed Assessment Tool (AGWA)) that can forecast net erosion as a function of sediment output for catchment erosion and sediment yield modeling. This review helps researchers and practitioners involved in erosion and sediment modeling by guiding the selection of an appropriate model type based on specific modeling purposes and basin scale. By choosing appropriate models, the accuracy and effectiveness of sediment yield estimation and erosion control measures can be improved.

25 June 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LZLiang Zhao
Liang Zhao
JLJixue Liu
Jixue Liu
SPStefan Peters
Stefan Peters
JLJiuyong Li
Jiuyong Li
SOSimon Oliver
Simon Oliver
NMNorman Mueller
Norman Mueller
Smoke plumes are the first things seen from space when wildfires occur. Thus, fire smoke detection is important for early fire detection. Deep Learning (DL) models have been used to detect fire smoke in satellite imagery for fire detection. However, previous DL-based research only considered lower spatial resolution sensors (e.g., Moderate-Resolution Imaging Spectroradiometer (MODIS)) and only used the visible (i.e., red, green, blue (RGB)) bands. To contribute towards solutions for early fire smoke detection, we constructed a six-band imagery dataset from Landsat 5 Thematic Mapper (TM) and Landsat 8 Operational Land Imager (OLI) with a 30-metre spatial resolution. The dataset consists of 1836 images in three classes, namely “Smoke”, “Clear”, and “Other_aerosol”. To prepare for potential on-board-of-small-satellite detection, we designed a lightweight Convolutional Neural Network (CNN) model named “Variant Input Bands for Smoke Detection (VIB_SD)”, which achieved competitive accuracy with the state-of-the-art model SAFA, with less than 2% of its number of parameters. We further investigated the impact of using additional Infra-Red (IR) bands on the accuracy of fire smoke detection with VIB_SD by training it with five different band combinations. The results demonstrated that adding the Near-Infra-Red (NIR) band improved prediction accuracy compared with only using the visible bands. Adding both Short-Wave Infra-Red (SWIR) bands can further improve the model performance compared with adding only one SWIR band. The case study showed that the model trained with multispectral bands could effectively detect fire smoke mixed with cloud over small geographic extents.

29 April 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SLSha Lu
Sha Lu
Eriita JonesEriita Jones
Eriita Jones
LZLiang Zhao
Liang Zhao
YSYu Sun
Yu Sun
Kai QinKai Qin
Kai Qin
SPStefan Peters
Stefan Peters
This article presents our research in the prelaunch phase of the Kanyini mission, which aims to implement an energy-efficient, AI-based system onboard for early fire smoke detection using hyperspectral imagery. Our approach includes three key components: developing a diverse hyperspectral training dataset from VIIRS imagery, groundwork in band selection and AI model preparation, and developing an emulation system. We adapted and evaluated our previously developed lightweight convolutional neural network model, VIB_SD, to meet the computational constraints of satellite deployment. The emulation system tests various onboard AI tasks and processes. Our comprehensive experiments demonstrate the feasibility and benefits of employing onboard AI for fire smoke detection, significantly improving downlink efficiency, energy consumption, and detection speed.

16 December 2021 in Geochemistry, Geophysics, Geosystems
Verified
Journal Article
Open access
PDF file
GSG. Sanchez
G. Sanchez
JHJ. A. Halpin
J. A. Halpin
MGM. Gard
M. Gard
DHD. Hasterok
D. Hasterok
TST. Stål
T. Stål
ABA. Burton‐Johnson
A. Burton‐Johnson
We present PetroChron Antarctica, a new relational database including petrological, geochemical and geochronological data sets along with computed rock properties from geological samples across Antarctica. The database contains whole‐rock geochemistry with major/trace element and isotope analyses, geochronology from multiple isotopic systems and minerals for given samples, as well as an internally consistent rock classification based on chemical analysis and derived rock properties (i.e., chemical indices, density, p‐velocity, and heat production). A broad range of meta‐information such as geographic location, petrology, mineralogy, age statistics and significance are also included and can be used to filter and assess the quality of the data. Currently, the database contains 11,559 entries representing 10,056 unique samples with varying amounts of geochemical and geochronological data. The distribution of rock types is dominated by mafic (36%) and felsic (33%) compositions, followed by intermediate (22%) and ultramafic (9%) compositions. Maps of age distribution and isotopic composition highlight major episodes of tectonic and thermal activity that define well known crustal heterogeneities across the continent, with the oldest rocks preserved in East Antarctica and more juvenile lithosphere characterizing West Antarctica. PetroChron Antarctica allows spatial and temporal variations in geology to be explored at the continental scale and integrated with other Earth‐cryosphere‐biosphere‐ocean data sets. As such, it provides a powerful resource ready for diverse applications including plate tectonic reconstructions, geological/geophysical maps, geothermal heat flow models, lithospheric and glacial isostasy, geomorphology, ice sheet reconstructions, biodiversity evolution, and oceanography.

6 February 2024 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
LZLiang Zhao
Liang Zhao
JLJixue Liu
Jixue Liu
SPStefan Peters
Stefan Peters
JLJiuyong Li
Jiuyong Li
NMNorman Mueller
Norman Mueller
SOSimon Oliver
Simon Oliver

13 May 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SPStefan Peters
Stefan Peters
JLJixue Liu
Jixue Liu
GKGunnar Keppel
Gunnar Keppel
AWAnna Wendleder
Anna Wendleder
PXPeiliang Xu
Peiliang Xu
Landslides, resulting from disturbances in slope equilibrium, pose a significant threat to landscapes, infrastructure, and human life. Triggered by factors such as intense precipitation, seismic activities, or volcanic eruptions, these events can cause extensive damage and endanger nearby communities. A comprehensive understanding of landslide characteristics, including spatio-temporal patterns, dimensions, and morphology, is vital for effective landslide disaster management. Existing remote sensing approaches mostly use either optical or synthetic aperture radar sensors. Integrating information from both these types of sensors promises greater accuracy for identifying and locating landslides. This study proposes a novel approach, the ML-LaDeCORsat (Machine Learning-based coseismic Landslide Detection using Combined Optical and Radar Satellite Imagery), that integrates freely available Sentinel-1, Palsar-2, and Sentinel-2 imagery data in Google Earth Engine (GEE). The approach also integrates relevant spectral indices and suitable bands used in a machine learning-based classification of coseismic landslides. The approach includes a robust and reproducible training and validation strategy and allows one to choose between five classifiers (CART, Random Forest, GTB, SVM, and Naive Bayes). Using landslides from four different earthquake case studies, we demonstrate the superiority of our approach over existing solutions in coseismic landslide identification and localization, providing a GTB-based detection accuracy of 87–92%. ML-LaDeCORsat can be adapted to other landslide events (GEE script is provided). Transfer learning experiments proved that our model can be applied to other coseismic landslide events without the need for additional training data. Our novel approach therefore facilitates quick and reliable identification of coseismic landslides, highlighting its potential to contribute towards more effective disaster management.