Dataset Information

Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland.

ABSTRACT: 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.

SUBMITTER: Amoakoh AO

PROVIDER: S-EPMC8153014 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Tropical peatlands are important carbon stores that are vulnerable to drainage and conversion to agriculture. Protection and restoration of peatlands are increasingly recognised as key nature based solutions that can be implemented as part of climate change mitigation. Identification of peatland areas that are important for protection and restauration with regards to the state of their carbon stocks, are therefore vital for policy makers. In this paper we combined organic geochemical analysis by Rock-Eval (6) pyrolysis of peat collected from sites with different land management history and optical remote sensing products to assess if remotely sensed data could be used to predict peat conditions and carbon storage. The study used the North Selangor Peat Swamp forest, Malaysia, as the model system. Across the sampling sites the carbon stocks in the below ground peat was ca 12 times higher than the forest (median carbon stock held in ground vegetation 114.70 Mg ha-1 and peat soil 1401.51 Mg ha-1). Peat core sub-samples and litter collected from Fire Affected, Disturbed Forest, and Managed Recovery locations (i.e. disturbed sites) had different decomposition profiles than Central Forest sites. The Rock-Eval pyrolysis of the upper peat profiles showed that surface peat layers at Fire Affected, Disturbed Forest, and Managed Recovery locations had lower immature organic matter index (I-index) values (average I-index range in upper section 0.15 to -0.06) and higher refractory organic matter index (R -index) (average R-index range in upper section 0.51 to 0.65) compared to Central Forest sites indicating enhanced decomposition of the surface peat. In the top 50 cm section of the peat profile, carbon stocks were negatively related to the normalised burns ratio (NBR) (a satellite derived parameter) (Spearman's rho = -0.664, S = 366, p-value = <0.05) while there was a positive relationship between the hydrogen index and the normalised burns ratio profile (Spearman's rho = 0.7, S = 66, p-value = <0.05) suggesting that this remotely sensed product is able to detect degradation of peat in the upper peat profile. We conclude that the NBR can be used to identify degraded peatland areas and to support identification of areas for conversation and restoration.

Project description:BackgroundClostridiales and Bacteroidales are uniquely adapted to the gut environment and have co-evolved with their hosts resulting in convergent microbiome patterns within mammalian species. As a result, members of Clostridiales and Bacteroidales are particularly suitable for identifying sources of fecal contamination in environmental samples. However, a comprehensive evaluation of their predictive power and development of computational approaches is lacking. Given the global public health concern for waterborne disease, accurate identification of fecal pollution sources is essential for effective risk assessment and management. Here, we use random forest algorithm and 16S rRNA gene amplicon sequences assigned to Clostridiales and Bacteroidales to identify common fecal pollution sources. We benchmarked the accuracy, consistency, and sensitivity of our classification approach using fecal, environmental, and artificial in silico generated samples.ResultsClostridiales and Bacteroidales classifiers were composed mainly of sequences that displayed differential distributions (host-preferred) among sewage, cow, deer, pig, cat, and dog sources. Each classifier correctly identified human and individual animal sources in approximately 90% of the fecal and environmental samples tested. Misclassifications resulted mostly from false-positive identification of cat and dog fecal signatures in host animals not used to build the classifiers, suggesting characterization of additional animals would improve accuracy. Random forest predictions were highly reproducible, reflecting the consistency of the bacterial signatures within each of the animal and sewage sources. Using in silico generated samples, we could detect fecal bacterial signatures when the source dataset accounted for as little as ~ 0.5% of the assemblage, with ~ 0.04% of the sequences matching the classifiers. Finally, we developed a proxy to estimate proportions among sources, which allowed us to determine which sources contribute the most to observed fecal pollution.ConclusionRandom forest classification with 16S rRNA gene amplicons offers a rapid, sensitive, and accurate solution for identifying host microbial signatures to detect human and animal fecal contamination in environmental samples.

Project description:Avian species persistence in a forest patch is strongly related to the degree of isolation and size of a forest patch and the vegetation structure within a patch and its matrix are important predictors of bird habitat suitability. A combination of space-borne optical (Landsat), ALOS-PALSAR (radar), and airborne Light Detection and Ranging (LiDAR) data was used for assessing variation in forest structure across forest patches that had undergone different levels of forest degradation in a logged forest-agricultural landscape in Southern Laos. The efficacy of different remote sensing (RS) data sources in distinguishing forest patches that had different seizes, configurations, and vegetation structure was examined. These data were found to be sensitive to the varying levels of degradation of the different patch categories. Additionally, the role of local scale forest structure variables (characterized using the different RS data and patch area) and landscape variables (characterized by distance from different forest patches) in influencing habitat preferences of International Union for Conservation of Nature (IUCN) Red listed birds found in the study area was examined. A machine learning algorithm, MaxEnt, was used in conjunction with these data and field collected geographical locations of the avian species to identify the factors influencing habitat preference of the different bird species and their suitable habitats. Results show that distance from different forest patches played a more important role in influencing habitat suitability for the different avian species than local scale factors related to vegetation structure and health. In addition to distance from forest patches, LiDAR-derived forest structure and Landsat-derived spectral variables were important determinants of avian habitat preference. The models derived using MaxEnt were used to create an overall habitat suitability map (HSM) which mapped the most suitable habitat patches for sustaining all the avian species. This work also provides insight that retention of forest patches, including degraded and isolated forest patches in addition to large contiguous forest patches, can facilitate bird species retention within tropical agricultural landscapes. It also demonstrates the effective use of RS data in distinguishing between forests that have undergone varying levels of degradation and identifying the habitat preferences of different bird species. Practical conservation management planning endeavors can use such data for both landscape scale monitoring and habitat mapping.

Project description:: Individuals with alcohol use disorder (AUD) manifest a variety of impairments that can be attributed to alterations in specific brain networks. The current study aims to identify features of EEG-based functional connectivity, neuropsychological performance, and impulsivity that can classify individuals with AUD (N = 30) from unaffected controls (CTL, N = 30) using random forest classification. The features included were: (i) EEG source functional connectivity (FC) of the default mode network (DMN) derived using eLORETA algorithm, (ii) neuropsychological scores from the Tower of London test (TOLT) and the visual span test (VST), and (iii) impulsivity factors from the Barratt impulsiveness scale (BIS). The random forest model achieved a classification accuracy of 80% and identified 29 FC connections (among 66 connections per frequency band), 3 neuropsychological variables from VST (total number of correctly performed trials in forward and backward sequences and average time for correct trials in forward sequence) and all four impulsivity scores (motor, non-planning, attentional, and total) as significantly contributing to classifying individuals as either AUD or CTL. Although there was a significant age difference between the groups, most of the top variables that contributed to the classification were not significantly correlated with age. The AUD group showed a predominant pattern of hyperconnectivity among 25 of 29 significant connections, indicating aberrant network functioning during resting state suggestive of neural hyperexcitability and impulsivity. Further, parahippocampal hyperconnectivity with other DMN regions was identified as a major hub region dysregulated in AUD (13 connections overall), possibly due to neural damage from chronic drinking, which may give rise to cognitive impairments, including memory deficits and blackouts. Furthermore, hypoconnectivity observed in four connections (prefrontal nodes connecting posterior right-hemispheric regions) may indicate a weaker or fractured prefrontal connectivity with other regions, which may be related to impaired higher cognitive functions. The AUD group also showed poorer memory performance on the VST task and increased impulsivity in all factors compared to controls. Features from all three domains had significant associations with one another. These results indicate that dysregulated neural connectivity across the DMN regions, especially relating to hyperconnected parahippocampal hub as well as hypoconnected prefrontal hub, may potentially represent neurophysiological biomarkers of AUD, while poor visual memory performance and heightened impulsivity may serve as cognitive-behavioral indices of AUD.

Dataset Information

Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets