Earth Science Research, Issue: Vol.15, No.1

Estimation of Chlorophyll-a from Case-2 Inland Waters: Comparing Two Analytical Algorithms

Tue, 30 Dec 2025 07:46:41 +0000

The paper draws on two different reflective band-ratio algorithms, namely the Maximum Chlorophyll-a Index (MCI) and New Three Band Algorithm (N3B) to estimate Chlorophyll-a (Chl-a) concentrations from Landsat-8 images and spectrometric water samples. Band tuning procedures was performed to find optimal peak wavelengths suitable for the estimation of Chl-a from Landsat-8 satellite image and spectrometric data. Additionally, the MCI and N3B were applied on both in-situ and Landsat-8 data and compared using statistical regression models such as the coefficient of determination (R²), relative mean absolute error (rMAE), and root mean square error (RMSE) to find the best performing algorithm in estimating Chl-a pigments. The results demonstrates that the MCI algorithm performed sensitively in the estimation of Chl-a as compared to the N3B, after data regression. The MCI algorithm obtained a higher R² of 0.69, with a minimal percentage error (rMAE) of 18.34% and RMSE of 1.85 m^-1 when applied on in-situ data. A similar result was obtained when MCI was applied on Landsat-8 data with a higher R² of 0.75 and a minimal percentage error (rMAE) of 21.29% and an RMSE of 0.97 m^-1, respectively. However, the N3B algorithm returned a lower R² of 0.54 and 0.65 when applied on both in-situ and Landsat-8 data concurrently. The standard errors for MCI were comparatively lower than that of the N3B. Hence, in this study, the MCI algorithm performed better because it has less predictive error. In all, although both algorithms were able to estimate Chl-a pigments, the MCI algorithm is more sensitive in the retrieval of Chl-a concentration from Case-2 inland waters using both in-situ and Landsat-8 data. The results indicate the high potential of analytical algorithms to estimate Chl-a concentration in turbid and eutrophic productive (Case II) waters using satellite data, which will be of immense value to scientists, natural resource managers, and decision makers involved in managing the inland aquatic ecosystems.

Modelling the Livelihood Vulnerability Index (LVI-IPCC) with Machine Learning in Agro-Ecological Region I of Southern Zambia

Sun, 04 Jan 2026 06:46:58 +0000

This study employed seven machine-learning algorithms: Random Forest, XGBoost, LightGBM, Support Vector Machine (SVM-RBF), Elastic Net, Multilayer Perceptron (MLP), and hybrid PCA-enhanced models to predict the Livelihood Vulnerability Index (LVI-IPCC) of smallholder farmers in Southern Zambia’s Agro-Ecological Region I. Using grouped cross-validation to prevent spatial bias, the PCA-MLP and Random Forest models emerged as top performers, achieving R² values above 0.95 and RMSE below 0.05. These models effectively captured nonlinear socio-ecological interactions that influence vulnerability. Feature importance analyses identified education, income, water access, and drought exposure as key predictors. The integration of dimensionality reduction (PCA) improved model stability and interpretability. These findings demonstrate that hybrid machine-learning approaches outperform traditional LVI aggregation in predicting household vulnerability, providing scalable, data-driven insights for climate adaptation planning. The results highlight the potential of artificial intelligence to revolutionize vulnerability assessments and inform targeted resilience strategies in regions affected by climate change.

Exploring the Potentials of Calcined Clay as A Partial Clinker Substitute for the Environmental Sustainability of Cement: A Case Study of Foreke Dschang Clays, West Cameroon

Sun, 29 Mar 2026 02:52:38 +0000

The aim of this study was to experimentally investigate the feasibility of using calcined clay as partial clinker substitute for sustainable cement manufacturing without compromising the performance of the cement. Clay sample were collected from Foreke Dschang. This clay underwent chemical analysis before and after calcination at 750 °C. For this calcined clay, the loss on ignition is negligible, its Σ(SiO₂+Al₂O₃ +Fe₂O₃) ˃ 70 %, amorphous phase is present. These properties allow this calcined clay to be classified as a supplementary cementitious material (SCM). The cement samples were prepared by substituting 10%, 20%, 30%, and 40% of clinker with calcined clay (respectively CEM A, CEM B, CEM C and CEM D), and were tested in comparison to two control formulations substituting clinker at 17% and 25% with volcanic ash (LION and EXTRA respectively). The increase in the calcined clay content resulted in an increase in the water/cement ratio and the initial setting time. CEM A, CEM B and CEM C displayed good compressive strength, comparable to LION (42.5R) and EXTRA (32.5R) respectively. Furthermore, in comparison with LION cement, CEM B shows an increase in compressive strength of 12.6% and 2.55% at 2 and 28 days respectively, despite a 3% clinker deficiency. Also, in comparison with EXTRA cement, CEM C shows an increase in compressive strength of 12.14% and 3.51% at 2 and 28 days respectively, despite a 5% clinker deficiency. This reduction of 3 to 5 % clinker consumption reduced the carbon footprint of the cement industry.