Methods for network leakage estimation include water balance, component analysis and minimum night flow (MNF) methods, the latter of which involves subtracting the customer night use (QCNU) from night leakage and multiplying by the hour day factor (HDF). QCNU and HDF respectively depend on Active Night Population (ANP) and leakage exponent (N1). In most developing countries, these parameters are assumed in the MNF method, thus introducing errors which makes setting realistic leakage reduction targets and key performance indicators (KPI) problematic. In this study, QCNU and HDF were evaluated by determining the relative error associated with ANP and N1 to establish localized rates for accurately estimating leakage in water networks. Between 7 and 11% relative error was associated with every 1% higher or lower ANP while up to 4% relative error was observed for every step considered. A linear relationship exists between the relative error associated with both and ANP although that of ANP is twice as high as This has technical implications for setting water loss reduction targets and investing in the water infrastructure. It is recommended that water utilities must establish localized ANP and values for accurate leakage estimation in water networks.

Water networks lose significant volumes of water from the distribution network. This is because most water networks, especially in developing countries, do not…

The ability to easily detect leaks in water networks enables prompt repairs thereby reducing the duration of a leak. This study uses a minimization approach re…

Crop diseases pose a significant risk to agricultural productivity, particularly in sub‐Saharan Africa, where cassava ( Manihot esculenta ), plantain ( Musa paradisiaca ), and cocoa ( Theobroma cacao ) serve as essential crops. There is an urgent need for innovative plant disease detection methods to enhance control measures and preventive strategies to address this menace, as these diseases threaten food security and economic stability in the growing regions. Image recognition, powered by deep learning (DL) models, offers a cost‐effective and scalable technology for disease detection. Thus, technological convergence has led to significant improvements in AI‐assisted plant disease diagnosis. This review evaluates the efficacy of convolutional neural networks (CNNs) for disease detection in these crops, focusing on model architecture, classification capability, and performance metrics such as accuracy, precision, recall, and F1‐score. A comparative analysis of CNN models and machine learning techniques highlights their robustness in detecting diseases like Black Sigatoka, Cassava Mosaic Disease, and Black Pod Disease. Additionally, this study examines the current challenges and limitations in crop disease detection and explores future directions, including the potential for transfer learning and expanded datasets to enhance model accuracy and generalizability. The goal is to improve crop disease detection accuracy, which is a critical step in ensuring the agricultural sector’s viability. The study expects that by greatly increasing detection rates, a strong basis for better disease management techniques will be established, guaranteeing the productivity and health of crops and, consequently, bolstering the financial stability of farming communities that depend on crop production. Results highlight CNNs as a strong foundation for early crop disease identification, supporting the advancement of precision agriculture applications in the region.