Analysis of land use and land cover change using machine learning algorithm in Yola North Local Government Area of Adamawa State, Nigeria.

The dynamic use of land that results from urbanization has an impact on the urban ecosystem. Yola North Local Government Area (Yola North LGA) of Adamawa state, Nigeria, has experienced tremendous changes in its land use and land cover (LULC) over the past two decades due to the influx of people from rural areas seeking for the benefits of its economic activities. The goal of this research is to develop an efficient and accurate framework for continuous monitoring of land use and land cover (LULC) change and quantify the transformation in land use and land cover pattern over a specific period (between 2002 and 2022). Land sat images of 2002, 2012, and 2022 were obtained, and the Support Vector Machine classification method was utilized to stratify the images. Land Change Modeler (LCM) tool in Idrissi Selva software was then used to analyze the LULC change. SVM produced a good classification result for all three years, with 2022 having the highest overall accuracy of 95.5%, followed by 2002 with 90% and 2012 with 87.7% which indicates the validity of the algorithm for future predictions. The results showed that severe land changes have occurred over the course of two decades in built-up (37.32%), vegetation (forest, scrubland, and grassland) (-3.27%), bare surface (-33.47%), and water bodies (-0.59%). Such changes in LULC could lead to agricultural land lost and reduced food supply. This research develops a robust framework for continuous land use monitoring, utilizing machine learning and geo-spatial data for urban planning, natural resource management, and environmental conservation. In conclusion, this study underscores the efficacy of support vector machine algorithm in analyzing complex land use and land cover changes.

Prevalence of Anxiety and Depression Among the General Population in Africa During the COVID-19 Pandemic: A Systematic Review and Meta-Analysis.

Background: Medical and socio-economic uncertainties surrounding the COVID-19 pandemic have had a substantial impact on mental health. This study aimed to systematically review the existing literature reporting the prevalence of anxiety and depression among the general populace in Africa during the COVID-19 pandemic and examine associated risk factors. Methods: A systematic search of the following databases African Journal Online, CINAHL, PubMed, Scopus, and Web of Science was conducted from database inception until 30th September 2021. Studies reporting the prevalence of anxiety and/or depression among the general populace in African settings were considered for inclusion. The methodological quality of included studies was assessed using the Agency for Healthcare Research and Quality (AHRQ). Meta-analyses on prevalence rates were conducted using Comprehensive Meta-analysis software. Results: Seventy-eight primary studies (62,380 participants) were identified from 2,325 studies via electronic and manual searches. Pooled prevalence rates for anxiety (47%, 95% CI: 40-54%, I2 = 99.19%) and depression (48%, 95% CI: 39-57%, I2 = 99.45%) were reported across Africa during the COVID-19 pandemic. Sex (female) and history of existing medical/chronic conditions were identified as major risk factors for anxiety and depression. Conclusions: The evidence put forth in this synthesis demonstrates the substantial impact of the pandemic on the pervasiveness of these psychological symptoms among the general population. Governments and stakeholders across continental Africa should therefore prioritize the allocation of available resources to institute educational programs and other intervention strategies for preventing and ameliorating universal distress and promoting psychological wellbeing. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021228023, PROSPERO CRD42021228023.