Groundwater models are valuable tools to quantify the response of groundwater level to hydrological stresses induced by climate variability and groundwater extraction. These models strive for sustainable groundwater management by balancing recharge, discharge, and natural processes, with groundwater level serving as a critical response variable. While traditional numerical models are labour-intensive, machine learning and deep learning offer a data-driven alternative, learning from historical data to predict groundwater level variations. The groundwater level in wells is typically recorded as continuous groundwater level time series data and is essential for implementing managed aquifer recharge within a particular region. Machine learning and deep learning are essential tools to generate a data-driven approach to modeling an area, and there is a need to understand if they are the most suitable tools to improve model prediction. To address this objective, the study evaluates two machine learning algorithms - Random Forest (RF) and Support Vector Machine (SVM); and two deep learning algorithms - Simple Recurrent Neural Network (SimpleRNN) and Long Short-Term Memory (LSTM) for modeling groundwater level changes in the West Coast Aquifer System of South Africa. Analysis of regression error metrics on the test dataset revealed that SVM outperformed the other models in terms of the root mean square error, whereas random forest had the best performance in terms of the MAE. In the accuracy analysis of predicted groundwater levels, SVM achieved the highest accuracy with an MAE of 0.356 m and an RMSE of 0.372 m. The study concludes that machine learning and deep learning are effective tools for improved modeling and prediction of groundwater level. Further research can incorporate more detailed geologic information of the study area for enhanced interpretation.

Background: Plasmodium falciparum-resistance to sulphadoxine-pyrimethamine (SP) has been largely reported among pregnant women. However, the profile of resistance markers to SP dihydrofolate reductase (dhfr) and dihydropteroate synthase (dhps) in the general population are varied and not frequently monitored. Currently, SP is used as partner drug for artemisinin combination therapy (SP-artesunate) in some sub-Saharan African countries or as a prophylactic drug in intermittent preventive treatment of malaria during pregnancy and infants and in seasonal malaria chemoprevention (SMC). Profiling of P. falciparum-resistant genotypes to SP is dynamic and critical in providing data that would be useful for malaria control programmes. This study assessed the profile of dhfr and dhps genes genotypes among individuals with malaria in Lagos, Nigeria. Methods: Molecular markers of SP resistance were identified by nested PCR and sequenced among malaria positive dried blood spots (DBS) that were collected from individuals attending health facilities from January 2013 to February 2014 and during community surveys from October 2010 to September 2011 across different Local Government Areas of Lagos State, Nigeria. Results: A total of 242 and 167 samples were sequenced for dhfr and dhps, respectively. Sequence analysis of dhfr showed that 95.5% (231/242), 96.3% (233/242) and 96.7% (234/242) of the samples had N51I, C59R and S108N mutant alleles, respectively. The prevalence of dhps mutation at codons A437G, A613S, S436A, A581G, I431V and K540E were 95.8% (160/167), 41.9% (70/167), 41.3% (69/167), 31.1% (52/167), 25.1% (42/167), and 1.2% (2/167) respectively. The prevalence of triple mutations (CIRNI) in dhfr was 93.8% and 44.3% for the single dhps haplotype mutation (SGKAA). Partial SP-resistance due to quadruple dhfr-dhps haplotype mutations (CIRNI-SGKAA) and octuple haplotype mutations (CIRNI-VAGKGS) with rate of 42.6% and 22.0%, respectively has been reported. Conclusions: There was increased prevalence in dhfr triple haplotype mutations when compared with previous reports in the same environment but aligned with high prevalence in other locations in Nigeria and other countries in Africa. Also, high prevalence of dhfr and dhps mutant alleles occurred in the study areas in Lagos, Nigeria five to eight years after the introduction of artemisinin combination therapy underscores the need for continuous monitoring.

The Lagos Lagoon is under increased pressure from growth in human population, growing demands for natural resources, human activities, and socioeconomic factors. The degree of these activities and the impacts are directly proportional to urban expansion and growth. In the light of this situation, the objectives of this study were: (i) to estimate through satellite imagery analysis the extent of changes in the Lagos Lagoon environment for the periods 1984, 2002, 2013 and 2019 using Landsat-derived data on land cover, Land Surface Temperature (LST), Normalised Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI); and (ii) to evaluate the relationship between the derived data and determine their relative influence on the lagoon environment. The derived data were subjected to descriptive statistics, and relationships were explored using Pearson's correlation and regression analysis. The effect of land cover on LST was measured using the Contribution Index and a trend analysis was carried out. From the results, the mean LSTs for the four years were 22.68°C (1984), 24.34°C (2002), 26.46°C (2013) and 28.40°C (2019). Generally, the mean LSTs is in opposite trend with the mean NDVIs and EVIs as associated with their dominant land cover type. The strongest positive correlations were observed between NDVI and EVI while NDVI had the closest fit with LST in the regression. Built-up areas have the highest contributions to LST while vegetation had a cooling influence. The depletion in vegetative cover has compromised the biodiversity of this environment and efforts are required to reverse this trend.