Kwame Awuah

Dr. Kwame Awuah

Edge Hill University
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
13 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Alex Owusu AmoakohAlex Owusu Amoakoh
Alex Owusu Amoakoh
Paul AplinPaul Aplin
Paul Aplin
KAKwame Awuah
Kwame Awuah
IDIrene Delgado-Fernandez
Irene Delgado-Fernandez
CMCherith Moses
Cherith Moses
JMJustice C. Mensah
Justice C. Mensah
Tropical peatlands such as Ghana’s Greater Amanzule peatland are highly valuable ecosystems and under great pressure from anthropogenic land use activities. Accurate measurement of their occurrence and extent is required to facilitate sustainable management. A key challenge, however, is the high cloud cover in the tropics that limits optical remote sensing data acquisition. In this work we combine optical imagery with radar and elevation data to optimise land cover classification for the Greater Amanzule tropical peatland. Sentinel-2, Sentinel-1 and Shuttle Radar Topography Mission (SRTM) imagery were acquired and integrated to drive a machine learning land cover classification using a random forest classifier. Recursive feature elimination was used to optimize high-dimensional and correlated feature space and determine the optimal features for the classification. Six datasets were compared, comprising different combinations of optical, radar and elevation features. Results showed that the best overall accuracy (OA) was found for the integrated Sentinel-2, Sentinel-1 and SRTM dataset (S2+S1+DEM), significantly outperforming all the other classifications with an OA of 94%. Assessment of the sensitivity of land cover classes to image features indicated that elevation and the original Sentinel-1 bands contributed the most to separating tropical peatlands from other land cover types. The integration of more features and the removal of redundant features systematically increased classification accuracy. We estimate Ghana’s Greater Amanzule peatland covers 60,187 ha. Our proposed methodological framework contributes a robust workflow for accurate and detailed landscape-scale monitoring of tropical peatlands, while our findings provide timely information critical for the sustainable management of the Greater Amanzule peatland.

1 November 2018 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Closed access
KAKwame Awuah
Kwame Awuah
NNNils Nölke
Nils Nölke
MFMaximilian Freudenberg
Maximilian Freudenberg
BDB.N. Diwakara
B.N. Diwakara
VTV.P. Tewari
V.P. Tewari
CKChristoph Kleinn
Christoph Kleinn

15 October 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KAKwame Awuah
Kwame Awuah
Paul AplinPaul Aplin
Paul Aplin
CMChristopher Marston
Christopher Marston
IPIan Powell
Ian Powell
ISIzak P. J. Smit
Izak P. J. Smit
Savannah grazing lawns are a key food resource for large herbivores such as blue wildebeest (Connochaetes taurinus), hippopotamus (Hippopotamus amphibius) and white rhino (Ceratotherium simum), and impact herbivore densities, movement and recruitment rates. They also exert a strong influence on fire behaviour including frequency, intensity and spread. Thus, variation in grazing lawn cover can have a profound impact on broader savannah ecosystem dynamics. However, knowledge of their present cover and distribution is limited. Importantly, we lack a robust, broad-scale approach for detecting and monitoring grazing lawns, which is critical to enhancing understanding of the ecology of these vital grassland systems. We selected two sites in the Lower Sabie and Satara regions of Kruger National Park, South Africa with mesic and semiarid conditions, respectively. Using spectral and texture features derived from WorldView-3 imagery, we (i) parameterised and assessed the quality of Random Forest (RF), Support Vector Machines (SVM), Classification and Regression Trees (CART) and Multilayer Perceptron (MLP) models for general discrimination of plant functional types (PFTs) within a sub-area of the Lower Sabie landscape, and (ii) compared model performance for probabilistic mapping of grazing lawns in the broader Lower Sabie and Satara landscapes. Further, we used spatial metrics to analyse spatial patterns in grazing lawn distribution in both landscapes along a gradient of distance from waterbodies. All machine learning models achieved high F-scores (F1) and overall accuracy (OA) scores in general savannah PFTs classification, with RF (F1 = 95.73±0.004%, OA = 94.16±0.004%), SVM (F1 = 95.64±0.002%, OA = 94.02±0.002%) and MLP (F1 = 95.71±0.003%, OA = 94.27±0.003%) forming a cluster of the better performing models and marginally outperforming CART (F1 = 92.74±0.006%, OA = 90.93±0.003%). Grazing lawn detection accuracy followed a similar trend within the Lower Sabie landscape, with RF, SVM, MLP and CART achieving F-scores of 0.89, 0.93, 0.94 and 0.81, respectively. Transferring models to the Satara landscape however resulted in relatively lower but high grazing lawn detection accuracies across models (RF = 0.87, SVM = 0.88, MLP = 0.85 and CART = 0.75). Results from spatial pattern analysis revealed a relatively higher proportion of grazing lawn cover under semiarid savannah conditions (Satara) compared to the mesic savannah landscape (Lower Sabie). Additionally, the results show strong negative correlation between grazing lawn spatial structure (fractional cover, patch size and connectivity) and distance from waterbodies, with larger and contiguous grazing lawn patches occurring in close proximity to waterbodies in both landscapes. The proposed machine learning approach provides a novel and robust workflow for accurate and consistent landscape-scale monitoring of grazing lawns, while our findings and research outputs provide timely information critical for understanding habitat heterogeneity in southern African savannahs.

30 December 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
KAKwame Awuah
Kwame Awuah
Paul AplinPaul Aplin
Paul Aplin
IPIan Powell
Ian Powell
ISIzak Smith
Izak Smith
Accurate vegetation mapping is essential to enhance understanding of important ecosystem processes such as fire behaviour, nutrient cycling, plant community composition and mega-herbivore population dynamics in African savannahs.The inherent heterogeneity of savannah landscapes however creates significant challenges for accurate discrimination of vegetation components. Recent studies based on the use of optical remote sensing data favour very high spatial resolution (VHR) multi-spectral imagery for dealing with this challenge. However, such data are costly for use in operational management. Planet Labs, through Norway’s International Climate and Forests Initiative (NICFI) in partnership with Kongsberger Satellite Services (KSAT) and Airbus, now grant free access to high-resolution, analysis-ready mosaics of Planet imagery over the tropics, with great potential for fine-scale vegetation mapping. However, the spectral characteristics of these data are limited, with little knowledge of their ability to resolve the spectral similarity of heterogeneous savannah vegetation components. In parallel, Sentinel-2 samples a relatively high number of spectral bands, but has relatively coarse spatial resolution for dealing with the high spatial heterogeneity in African savannah landscapes. We test the hypothesis that fusing Sentinel-2 with Planet imagery leverages their spectral and spatial advantages to enhance accurate discrimination of savannah vegetation types. To achieve this, Principal Component and Gram-Schmidt transformations were compared for image fusion via pan-sharpening, where the Gram-Schmidt approach proved superior. Using this approach, we fused Sentinel-2 and Planet images and compared the three datasets (i.e. Sentinel-2, Planet and Fused images) augmented with two spectral indices and three Haralick texture features in a multi-layer perceptron neural network classification within a test site in the Lower Sabie region of Kruger National Park, South Africa. Overall, the Fused image achieved the best and most precise classification accuracy metrics (weighted F-score: 0.87±0.012) compared to Sentinel-2 (weighted F-score: 0.85±0.034) and Planet imagery (weighted F-score: 0.85±0.017). A comparison of classifications showed loss in spatial detail when using Sentinel-2 (at 10 meters spatial resolution), yet similar thematic details for vegetation classes across all three datasets. Our findings highlight the utility of Sentinel-2 and the Planet-NICFI mosaics in a heterogeneous savannah landscape, while setting a foundation for cost-effective and accurate high spatial resolution monitoring of savannah ecosystem.