Mark Hamilton

NIHR Bristol Cardiovascular Biomedical Research Unit

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Dave Hutchins

Geological Survey of Namibia

R. L. Evans

Woods Hole Oceanographic Institution

Mark Müller

Friedrich-Alexander-Universität Erlangen-Nürnberg

J. Spratt

Boston Children's Hospital

S. J. Webb

University of the Witwatersrand

Xavier García

Institut de Ciències del Mar

Alan G. Jones

Heart of England NHS Foundation Trust

Remy Dehaan

Charles Sturt University

J. Kelly

Charles Sturt University

Felipé Gonzalez

Queensland University of Technology

Cooperative Institutions

Electromagnetic Geoservices (Norway)

Dublin Institute For Advanced Studies

Council for Geoscience

Charles Sturt University

EarthTech International (United States)

University of Western Australia

De Beers (South Africa)

Queensland University of Technology

Woods Hole Oceanographic Institution

Commonwealth Scientific and Industrial Research Organisation

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Bitou bush detection and mapping using UAV-based multispectral and hyperspectral imagery and artificial intelligence

Remote Sensing Applications Society and Environment (2024)

A. Narmilan J. Kelly Juan Sandino Mark Hamilton Felipé Gonzalez

The use of Unmanned Aerial Vehicles (UAVs) for remote sensing (RS) of vegetation presents a valuable platform for weed monitoring, owing to the high spatial resolution of collected images. Accurate classification and mapping of weed spatial distribution plays a pivotal role in achieving effective management and ensures efficient and sustainable utilisation of weed control measures. Furthermore, UAV-based RS provides a rapid way of assessing phenological development stages of weed species such as flowering and fruiting. These are often critical stages required for the separation of weed species from surrounding vegetation and are difficult to capture with traditional low resolution airborne and satellite RS imagery. Bitou bush is a shrub and a serious environmental weed of coastal areas of New South Wales. The primary objective of this study is to develop a model for bitou bush mapping from collected multispectral (MS) and hyperspectral (HS) imagery on location in NSW, Australia by employing various classical machine learning (ML) and deep learning (DL) techniques. The performance of Random forests (RF), Support vector machine (SVM), Extreme gradient boosting (XGB), and K-nearest neighbors (KNN) models is evaluated, achieving overall validation accuracies of 78%, 74%, 80%, and 69%, respectively for bitou bush detection using MS imagery. Subsequently, these models are assessed on HS data, resulting in overall validation accuracies of 77%, 86%, 86%, and 80% for RF, SVM, XGB, and KNN, respectively. Moreover, the DL U-Net model achieved an overall validation accuracy of 92%, outperforming the classical ML models in MS data classification tasks. The results of this study highlight the superior performance of the U-Net model in comparison to classical ML models in RS data classification, indicating the value of DL techniques for more accurate and robust RS applications such as bitou bush detection and mapping. The insights gained from this research will aid researchers and land managers select appropriate models based on the complexity and characteristics of their RS datasets. Moreover, the integration of UAV RS and artificial intelligence (AI) provide a valuable and efficient platform for bitou bush monitoring and management practices, ultimately enhancing the efficiency and sustainability of weed control efforts.

10.1016/j.rsase.2024.101151

Cite

Citations (2)

Electrical lithosphere beneath the Kaapvaal craton, southern Africa

Journal of Geophysical Research Atmospheres (2011)

R. L. Evans Alan G. Jones Xavier García Mark Müller Mark Hamilton

[1] A regional-scale magnetotelluric (MT) experiment across the southern African Kaapvaal craton and surrounding terranes, called the Southern African Magnetotelluric Experiment (SAMTEX), has revealed complex structure in the lithospheric mantle. Large variations in maximum resistivity at depths to 200–250 km relate directly to age and tectonic provenance of surface structures. Within the central portions of the Kaapvaal craton are regions of resistive lithosphere about 230 km thick, in agreement with estimates from xenolith thermobarometry and seismic surface wave tomography, but thinner than inferred from seismic body wave tomography. The MT data are unable to discriminate between a completely dry or slightly “damp” (a few hundred parts per million of water) structure within the transitional region at the base of the lithosphere. However, the structure of the uppermost ∼150 km of lithosphere is consistent with enhanced, but still low, conductivities reported for hydrous olivine and orthopyroxene at levels of water reported for Kaapvaal xenoliths. The electrical lithosphere around the Kimberley and Premier diamond mines is thinner than the maximum craton thickness found between Kimberley and Johannesburg/Pretoria. The mantle beneath the Bushveld Complex is highly conducting at depths around 60 km. Possible explanations for these high conductivities include graphite or sulphide and/or iron metals associated with the Bushveld magmatic event. We suggest that one of these conductive phases (most likely melt-related sulphides) could electrically connect iron-rich garnets in a garnet-rich eclogitic composition associated with a relict subduction slab.

Xenolith

Magnetotellurics

Asthenosphere

10.1029/2010jb007883

Cite

Citations (112)

Area selection using magnetotellurics: examples from southern Africa

International Kimberlite Conference Extended Abstracts: 2008 (2019)

Alan G. Jones Mark Müller Mark Hamilton M. P. Miensopust Xavier García

1: Dublin Institute for Advanced Studies, 5 Merrion Square, Dublin, Ireland; 2: Department of Geology and Geo-physics, Woods Hole Oceanographic Institution, Clark South 172, 360 Woods Hole Road, Woods Hole, Massachu-setts, 02543-1542, U.S.A.; 3: Council for Geoscience, 280 Pr etoria Street, Silverton, Pretoria 0001, RSA; 4: Geo-logical Survey of Botswana, Private Bag 14, Lobatse, Botswana; 5: Geological Survey of Namibia, 1 Aviation Road, Windhoek, Namibia; 6: Council for Scientific and Industrial Research, Pretoria, RSA; 7: De Beers Group Services, Private Bag X01, Southdale 2135, South Africa; 8: Rio Tinto Mining and Exploration, London, U.K.; 9: BHP Billi-ton, Johannesburg, RSA; 10: University of the Witwatersrand, 6 Hollard Street, Johannesburg 2001, RSA; 11: ABB AB, HVDC, Ludvika, SE-77180, Sweden; 12: Other members of the SAMTEX team include: Louise Collins, Colin Hogg, Clare Horan, Jessica Spratt, Gerry Wallace (DIAS), Alan D. Chave (WHOI), Janine Cole, Raimund Stettler (CGS), G. Tshoso (GSB), Ed Cunion (RTME), David Khosa (BHPB) and Pieter-Eward Share (CSIR); 13: Now at EMGS, Stiklestadveien 1, N-7041 Trondheim, Norway.

Magnetotellurics

10.29173/ikc3603

Cite

Citations (0)

Autonomous Detection of Mouse-Ear Hawkweed Using Drones, Multispectral Imagery and Supervised Machine Learning

Remote Sensing (2023)

A. Narmilan Mark Hamilton J. Kelly Lihong Zheng Juan Sandino

Hawkweeds (Pilosella spp.) have become a severe and rapidly invading weed in pasture lands and forest meadows of New Zealand. Detection of hawkweed infestations is essential for eradication and resource management at private and government levels. This study explores the potential of machine learning (ML) algorithms for detecting mouse-ear hawkweed (Pilosella officinarum) foliage and flowers from Unmanned Aerial Vehicle (UAV)-acquired multispectral (MS) images at various spatial resolutions. The performances of different ML algorithms, namely eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Random Forest (RF), and K-nearest neighbours (KNN), were analysed in their capacity to detect hawkweed foliage and flowers using MS imagery. The imagery was obtained at numerous spatial resolutions from a highly infested study site located in the McKenzie Region of the South Island of New Zealand in January 2021. The spatial resolution of 0.65 cm/pixel (acquired at a flying height of 15 m above ground level) produced the highest overall testing and validation accuracy of 100% using the RF, KNN, and XGB models for detecting hawkweed flowers. In hawkweed foliage detection at the same resolution, the RF and XGB models achieved highest testing accuracy of 97%, while other models (KNN and SVM) achieved an overall model testing accuracy of 96% and 72%, respectively. The XGB model achieved the highest overall validation accuracy of 98%, while the other models (RF, KNN, and SVM) produced validation accuracies of 97%, 97%, and 80%, respectively. This proposed methodology may facilitate non-invasive detection efforts of mouse-ear hawkweed flowers and foliage in other naturalised areas, enabling land managers to optimise the use of UAV remote sensing technologies for better resource allocation.

Drone

10.3390/rs15061633

Cite

Citations (12)