Michael Appiah-Twum

Mr. Michael Appiah-Twum

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
9 December 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Michael Appiah-TwumMichael Appiah-Twum
Michael Appiah-Twum
WXWenbo Xu
Wenbo Xu
ESEmmanuel Daanoba Sunkari
Emmanuel Daanoba Sunkari
Remote sensing provides an efficient roadmap in geological analysis and interpretation. However, some challenges arise when remote sensing techniques are integrated with machine learning in geological surveys. Factors including irregular spatial distribution, sample imbalance, interclass resemblances, regolith, and geochemical similarities impede geological feature diagnosis, interpretation, and identification across varied remote sensing datasets. To address these limitations, a hybrid-attention-integrated long short-term memory (LSTM) network is employed to diagnose, interpret, and identify lithological feature representations in a remote sensing-based geological analysis using multisource data fusion. The experimental design integrates varied datasets including Sentinel-2A, Landsat-9, ASTER, ALOS PALSAR DEM, and Bouguer anomaly gravity data. The proposed model incorporates a hybrid attention mechanism (HAM) comprising channel and spatial attention submodules. HAM utilizes an adaptive technique that merges global-average-pooled features with max-pooled features, enhancing the model’s accuracy in identifying lithological units. Additionally, a channel separation operation is employed to allot refined channel features into clusters based on channel attention maps along the channel dimension. The comprehensive analysis of results from comparative extensive experiments demonstrates HAM-LSTM’s state-of-the-art performance, outperforming existing attention modules and attention-based models (ViT, SE-LSTM, and CBAM-LSTM). Comparing HAM-LSTM to baseline LSTM, the HAM module’s integrated configurations equip the proposed model to better diagnose and identify lithological units, thereby increasing the accuracy by 3.69%.

31 December 2018 in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
Verified
Journal Article
Open access
PDF file
ESEmmanuel Daanoba Sunkari
Emmanuel Daanoba Sunkari
Michael Appiah-TwumMichael Appiah-Twum
Michael Appiah-Twum
ALAbdurrahman Lermi
Abdurrahman Lermi
In this study, the spatial distribution of laterites in Kunche within the Wa-Lawra belt of NW Ghana, their trace element distributions, and geochemical associations were investigated. XRF and ICP-MS techniques were employed to generate the geochemical data and interpreted using multivariate geostatistical analysis. The laterites are classified as lateritic duricrust (residual laterites) and ferruginous duricrust (transported laterites). Three element associations (Fe, S, Pb-Group 1; Mn, Cu, Co, Cr, Ni, Ti, As, Au, Ag-Group 2; Ca, Rb, Sr, Zr, Y, Zn-Group 3) are observed from the multivariate geostatistical analysis implying that the element association in the area is directly related to secondary dispersion of the gold-bearing underlying meta-volcanic host rocks and laterization. Threshold values from medium absolute deviation method indicate anomalous concentrations in the laterites for S (>0.41%), Pb (>48 ppm), Cu (46 ppm), As (134.2 ppm), and Ag (>0.42 ppm), implying that these elements are the important pathfinder elements of gold identified in the laterites. However, multi-element mapping indicates that Pb + Cu + As + Ag is the best element association in the exploration of gold deposits. This association shows ellipsoidal anomalies in a contour map restricted to the environment of the residual laterites and similar to the gold distribution map.