Effective Quality Management Research Articles

Cost-effective control of air pollution in South Asia: Modeling and policy applications

Abstract Air pollution poses a critical environmental challenge to sustainability, environmental health and public well-being in the South Asia Region (SAR). This study identifies hotspots of fine particulate matter (PM2.5) across SAR, analyzing both concentration levels and exposure. Moreover, it aims at a comprehensive understanding of the various sources of air pollution in these critical areas and a systematic evaluation of the costs and benefits of relevant policy actions, utilizing the GAINS modeling framework. A wide variety of sources contribute to PM2.5 levels in ambient air, and effective air quality management requires a balance of measures across these sources. Current environmental policies, while effective in decoupling emissions from economic growth in SAR, are insufficient to achieve significant reductions in ambient PM2.5 concentrations. However, considerable scope exists for further measures beyond current policies that could help to bring the WHO Interim Targets (IT-1) for PM2.5 closer. Finally, it is shown that cost-optimal strategies for air quality management can achieve significant cost savings compared to conventional approaches; however, they require collaboration between states, regions and countries in South Asia.

A review of particulate matter (PM) in Indonesia: trends, health impact, challenges, and options.

This study reviews particulate matter (PM) research in Indonesia, focusing on current trends, health impacts, challenges, and future research directions. As the largest archipelago country, Indonesia faces severe pollution annually due to rapid urbanization, industrial activities, vehicle emissions, and forest fires. PM levels often exceed WHO and NAAQS standards, especially in urban areas and during forest fire seasons, posing significant health risks to vulnerable populations. Most PM studies have been conducted in major cities, primarily concentrated on Java Island. While there are several studies in Sumatra and Borneo, they commonly focus on the effects of peatland fires, and research in the eastern part of Indonesia remains limited. Substantial gaps in PM studies have been highlighted, including limited monitoring infrastructure, technology, data inconsistencies, and socio-economic challenges. Recent studies emphasize the need for more research on size-segregated PM, including ultrafine particles (UFPs), to fully understand their behavior in the atmosphere, sources, distribution, and health impacts. Chemical analysis and source apportionment studies are also crucial but currently limited due to equipment and analytical challenges. To improve PM management, the study proposes strategic options, including adopting advanced monitoring technologies along with low-cost samplers, increasing funding and technical training, enhancing coordination among stakeholders, and fostering international collaboration. Furthermore, public awareness campaigns and community-based monitoring are essential for effective air quality management.

The effect of transformer sizing and load variability on harmonics generated in a Nigerian university

This study investigates the impact of transformer sizing and load variability on the generation of harmonics in the distribution network of the Federal University of Technology, Akure (FUTA), Nigeria. The analysis focuses on Total Harmonic Distortion Voltage (THDv) at various Points of Common Coupling (PCCs) connected to different transformer capacities. Results indicate that PCCs linked to 500 kVA transformers exhibit THDv values ranging from 0.9% to 21.05%, generally falling within acceptable limits, albeit with some outliers. In contrast, PCCs associated with 200 kVA transformers display a broader and more concerning THDv range, from 0.65% to 65%. Additionally, the study reveals a significant increase in THDv at night compared to daytime, attributed to the higher prevalence of non-linear loads during off-peak hours. These findings highlight the critical role of transformer sizing and load patterns in managing harmonic distortion, underscoring the need for effective power quality management strategies within university distribution networks.

구조적 토픽 모델(STM) 분석을 활용한 수업 질 관리 방안 연구: A대학교 경영대학 강의평가 결과를 중심으로

This study aims to understand students' perceptions of lectures based on university lecture evaluation results and to analyze the correlation between differences in these perceptions depending on whether the average lecture evaluation scores are high or low, with the overarching goal of improving lecture quality. We employ Structural Topic Modeling (STM) for our analysis, and the findings are as follows. First, seven topics were extracted from our topic modeling: the professor's characteristics, satisfaction with the lecture, the professor's attitude toward the lecture, teaching methods, the difficulty level(complexity) of the lecture content, the pace of the lecture, and class evaluation. Second, there was a clear difference between topics in the higher and lower ranges of lectures evaluation scores. We found that the topics of "the professor's attitude toward the lecture" and "the difficulty level of the lecture content" were most strongly associated with other topics. In short, students in the business programs in our data evaluate lectures based primarily on 'teaching factors'. Thus, instructors teaching business courses should carefully reflect on ways to improve course-related aspects in their teaching. Additionally, for effective course quality management, professors should assess and improve the extent to which they are systematically organizing and preparing course designs in relation to the clarity of their content delivery, the degree of interest they express in their students, the organization of their teaching methods and lecture pace, and lecture evaluations.

Assessing road construction effects on turbidity in adjacent water bodies using Sentinel-1 and Sentinel-2

Road construction significantly affects water resources by introducing contaminants, fragmenting habitats, and degrading water quality. This study examines the use of Remote Sensing (RS) data of Sentinel-1 (S1) and Senitnel-2 (S2) in Google Earth Engine (GEE) to do spatio-temporal analysis of turbidity in adjacent water bodies during the construction and operation of the E18 Arendal-Tvedestrand highway in southeastern Norway from 2017 to 2021. S1 radiometric data helped delineate water extents, while S2-Top of Atmosphere (TOA) multispectral data, corrected using the Modified Atmospheric correction for INland waters (MAIN), used to estimate turbidity levels. To ensure a comprehensive time series of RS data, we utilized S2-TOA data corrected with the MAIN algorithm rather than S2-Bottom Of Atmosphere (BOA) data. We validated the MAIN algorithm's accuracy against GLORIA (Global Observatory of Lake Responses to Interventions and Drivers) observations of surface water reflectance in lakes, globally. Subsequently, the corrected S2 data is used to calculate turbidity using the Novoa and Nechad retrieval algorithms and compared with GLORIA turbidity observations. Findings indicate that the MAIN algorithm adequately estimates water-leaving surface reflectance (Pearson correlation > 0.7 for wavelengths between 490 and 705 nm) and turbidity (Pearson correlation > 0.6 for both algorithms), determining Nechad as the more effective algorithm. In this regard, we used S2 corrected images with MIAN to estimate turbidity in the study area and evaluated with local gauge data and observational reports. Results indicate that the proposed framework effectively captures trends and patterns of turbidity variation in the study area. Findings verify that road construction can increase turbidity in adjacent water bodies and emphasis the employing RS data in cloud platforms like GEE can provide insights for effective long-term water quality management strategies during construction and operation phases.

Geospatial Evaluation of Ambient Air Quality in Akure South Local Government Area, Ondo State, Nigeria

The study evaluates the ambient air quality in Akure South Local Government Area, Ondo State, Nigeria, focusing on particulate matter (PM2.5 and PM10) and its health implications on residents. Primary data were collected using Purple Air Monitor devices at 28 ground stations and structured questionnaires, base maps. The study utilized QGIS for mapping, SPSS for statistical analysis and WHO’s AirQ software for health risk assessment. Findings indicated exceedances of WHO and USEPA recommended limits for PM2.5 and PM10, with areas near major highways showing elevated PM levels. The health risk assessment revealed potential increases in hospitalizations and mortality due to air pollution. This research contributes uniquely by applying geospatial evaluation and health risk assessment tools for comprehensive air quality analysis. It highlights the urgent need for effective air quality management strategies, including the deployment of air quality monitoring stations and public education campaigns. The study provides crucial insights for policy makers, emphasizing the importance of mitigating air pollution’s adverse effects on urban settings. Received: 15 September 2024 / Accepted: 8 November 2024 / Published: 20 November 2024

Dataset on heavy metal pollution assessment in freshwater ecosystems

Water quality degradation due to heavy metal contamination poses serious threats to both human health and aquatic ecosystems. The rise in the concentration of heavy metals in aquatic environments is largely attributable to anthropogenic activities. These metals accumulate over time in water bodies, necessitating rigorous monitoring to accurately assess pollution levels. The present study is concerned with the assessment of heavy metal pollution in the Styr River (Ukraine) before and after the discharge of water from a nuclear power plant. The assessment is based on three indices: the Heavy Metal Pollution Index, the Heavy Metal Evaluation Index, and the Degree of Contamination. Therefore, heavy metals, including zinc (Zn), cadmium (Cd), lead (Pb), copper (Cu), nickel (Ni), manganese (Mn), arsenic (As) and chromium (Cr), were analyzed in this study. Water samples were collected at two locations on a monthly basis over the course of five years (2018–2022) and subsequently analysed using inductively coupled plasma optical emission spectroscopy. The results indicates a low contamination level at both sampling sites, indicating stable and uniform concentrations of metals across the study area. Moreover, statistical analysis highlights significant associations between certain metals and pollution indices, supporting the indices’ utility in tracking pollution trends and assessing environmental impacts. This dataset underscores the importance of ongoing monitoring for effective water quality management.

Evaluation of Learning Management Standards to Improve Higher Education Quality Standards Through Internal Quality Audits

Independent evaluation is required through an internal quality control system through internal quality audit activities. This study evaluated the achievement of learning management standards, inhibiting factors, and recommendations for improving education quality standards at Palembang Polytechnic. This type of qualitative research uses observation methods, structured interviews, and literature studies. The research instrument is the author directly involved in the research. The informants in this study were determined using a purposive technique: three research informants. The study’s results obtained data on implementing internal quality audits on learning management standards that have not been implemented. An effective internal quality management model is needed as a platform or application that supports collecting, storing, and managing data and information on website-based internal quality management system services to support fast, precise, and efficient internal quality management system integration.

Discriminative characteristics of hydrochemical components and sedimentary organic matter in Korean coastal aquaculture systems during summer

Understanding the spatial distribution and sources of sedimentary organic matter (OM) in coastal environments is crucial for effective water quality management and the preservation of ecosystem health. Although extensive research has been conducted on OM dynamics, there remains a gap in understanding the ongoing biogeochemical processes in Korean coastal aquaculture zones, particularly during the summer season. To address this gap, we investigated the spatial variation of water chemical properties and isotopic composition of sedimentary OM to trace the composition, source, and reactivity of mixed OM in aquaculture systems along the Korean coast during the summer season. The isotopic approach was applied to surface sediments from five sections: western (W)-1, W-2, southern (S)-1, S-2, and eastern (E)-1. With respect to increased nutrients (mainly nitrate; 1.2 ± 0.6 mg/L) by dam-water discharge near W sections, our isotopic signatures revealed that a substantial fraction of sedimentary OM might dominantly originated from autochthonous OM source (algae; 36.5%) related to the increase of terrestrial nutrients. Simultaneously, the deposition of allochthonous OM (aquacultural feces; 44%) was predominant in the S-2 sections. The 34S-depleted patterns (approximately -7.2‰) in the S-2 section was indicative of active sulfate reduction occurring at the sedimentary boundary. Therefore, together with the precise determination of ongoing OM, our isotopic results provide valuable insights for effectively managing water-sedimentary qualities under the increase of anthropogenic contamination.

Enhancing Project Performance Through Quality (Toyyib) Dimensions: An Empirical Study in Jordan's Construction Industry

This study investigates the impact of key project quality (Toyyib) dimensions—Feasibility, Conformity, Durability, and Serviceability on project performance within Jordan's construction industry. Drawing from existing literature, the study highlights the critical link between quality management practices and enhanced project outcomes. Utilizing a quantitative research methodology and Structural Equation Modeling (SEM), data collected from 204 managers within Jordan’s construction firms reveal a significant positive relationship between effective quality management and improved project performance. The findings underscore the importance of comprehensive quality audits and robust quality control mechanisms in minimizing delays, reducing costs, and achieving project objectives. This research contributes to both theoretical perspectives and practical applications in construction management, advocating for the integration of systematic quality dimensions to drive competitive advantage and sustainable project success.

Understanding the relationship between land use/land cover changes and air quality: A GIS-based fuzzy inference system approach.

Air pollution is a global issue that demands urgent attention due to its detrimental effects on human health and the environment. Land Use and Land Cover (LULC) change is an essential factor that significantly impacts ambient air quality through alterations in emission sources, vegetation cover, natural processes, and urban design. This study investigates the spatio-temporal variation of key air pollutants resulting from urban LULC changes in the Delhi region. Findings reveal a notable increase in pollutant concentrations, particularly particulate matter, in 2019 (PM10: 318.65 ± 45.80 µg/m3) and 2023 (PM10: 383.70 ± 61.49 µg/m3), compared to 2008 (PM10: 246.76 ± 30.66). LULC change analysis demonstrates a rise in built-up areas 24.59%(2008 to 2019), 33.62% (2008 to 2023) and a decline in vegetation cover 27.49% (2008 to 2019),32.37% (2008 to 2023). Correlation analysis indicates a positive correlation between PM10 and urban indices (+ 0.63) and a negative correlation between PM10 and vegetation indices (- 0.61), highlighting the impact of LULC on air quality deterioration. Subsequently, a fuzzy inference system model integrates LULC information to develop an air quality index (AQI). Incorporating LULC changes in AQI assessment offers a realistic approach to address the complexity arising from combined air pollutant effects, surpassing conventional AQI calculation methods. The findings underscore the significance of understanding the impact of Land Use and Land Cover (LULC) change on ambient air quality in formulating effective air quality management programs and policies. Integrating this knowledge into policymaking is crucial for the successful abatement of air pollution in urbanized areas.

Light-duty gasoline vehicle emission deterioration insights from large-scale inspection/maintenance data: The synergistic impact of usage characteristics

Accurately estimating vehicle emissions is crucial for effective air quality management. As key data for emission inventory construction, emission factors (EFs) are influenced by vehicle usage characteristics and experience deterioration. Current deterioration models often employ single-factor approaches based on vehicle age or accumulated mileage, which fail to capture the effects of varying usage intensities within the same mileage or age intervals. This study addressed this limitation by developing a novel emission deterioration model that incorporates multi-dimensional usage characteristics and that utilizes a large-scale inspection and maintenance (I/M) dataset for light-duty gasoline vehicles (LDGVs). The modeling results reveal distinct deterioration patterns for different pollutants and highlight the synergistic effects of the usage duration and intensity: natural aging significantly impacts HC and NOx emissions, while CO emissions are more strongly affected by intensive use. Specifically, China V LDGVs that were driven 4 × 104 km/yr exhibited HC, CO, and NOx deterioration rates per mile that were approximately 4.1 % lower, 10.3 % higher, and 1.1 % higher, respectively, than those of vehicles driven 2 × 104 km/yr as the mileage increased from 5 × 104 km to 10 × 104 km. By leveraging timely emission data and explicitly accounting for usage intensity, this study corrected biases in local emission estimates by 5–85 % with respect to estimates from commonly used models. This framework enables the development of more effective control strategies and refinements to policy evaluations in megacities with I/M programs.

The Impact of Acute Ammonia Nitrogen Stress on Serum Biochemical Indicators and Spleen Gene Expression in Juvenile Yellowfin Tuna (Thunnus albacares).

The presence of ammonia nitrogen in water has a significant impact on the serum and spleen of fish, potentially leading to changes in substances such as proteins in the serum while also causing damage to the immune function of the spleen. To investigate the effects of ammonia nitrogen (NH3-N) stress on juvenile yellowfin tuna (Thunnus albacares), this study established three NH3-N concentrations, 0, 5, and 10 mg/L, denoted as L0, L1, and L2, respectively. Serum and spleen samples were collected at 6, 24, and 36 h. The effects of different NH3-N concentrations and exposure times on the physiological status of juvenile fish were investigated by analyzing serum biochemical indices and splenic gene expression. The results indicate that in the L1 group, the serum high-density lipoprotein cholesterol (HDL-C), triglycerides (TG), complement 3 (C3) and complement 4 (C4) levels, and acid phosphatase (ACP) activity showed a trend of initially increasing and then decreasing. In the L2 group, the serum low-density lipoprotein cholesterol (LDL-C), HDL-C, and C4 levels and ACP activity also displayed an initially rising and then declining trend, while TG, C3, and creatinine (CRE) levels and alkaline phosphatase (AKP) activity showed an upward trend. In the L1 group, glutathione peroxidase 1b (GPX1b), interleukin 10 (IL-10), interleukin 6 receptor (IL-6r), and tumor necrosis factor alpha (TNF-α) gene expression levels in the spleen exhibited a trend of first increasing and then decreasing. In the L2 group, IL-10, IL-6r, tumor necrosis factor beta (TNF-β), caspase 2 (casp2), and caspase 9 (casp9) gene expression levels in the spleen also showed an initial increase followed by a decrease. When NH3-N levels are below 5 mg/L, it is recommended to limit stress exposure to no more than 36 h for the juvenile fish. For concentrations ranging from 5 to 10 mg/L, stress should be strictly controlled to within 24 h. Exposure to high NH3-N levels may affect biochemical indicators such as serum lipid metabolism, immunity, and metabolism in juvenile fish, and may damage the expression of antioxidant, immune gene, and apoptosis factors in the spleen. This study aims to deepen our understanding of the effects of NH3-N on juvenile tuna, with the goal of establishing effective water quality monitoring and management strategies. This will ensure the quality of aquaculture water, reduce the harm caused by NH3-N to juvenile yellowfin tuna, and enhance aquaculture efficiency and product quality.

Assessment of Environmental Pollutants and their Relationship with Chronic Respiratory Disease Exacerbations in Jamshoro: A Cross-Sectional Study

Background: COPD and Asthma are a burden to our society and in a city like Jamshoro having industries and power plants in close vicinity, this becomes a greater concern. The objective of this cross-sectional study was to evaluate the relationship between air quality indices (AQIs) and exacerbations in chronic obstructive respiratory diseases such as asthma and COPD, prevalent among the general population in Jamshoro. Methods: This cross-sectional study, conducted from August 2023 to February 2024 at LUMHS, Jamshoro (ERC approval: 14287/23/081), used purposive sampling to recruit 300 adults with asthma or COPD. Air quality data (PM10, PM2.5, NO2, SO2) were collected, and respiratory outcomes were measured via spirometry and a validated questionnaire. Pearson’s correlation and multiple regression analyzed the association between air quality and exacerbations. Ethical approval and informed consent were obtained. Results: There was a significant inverse relationship between PM10, NO2, and FEV1 (r = -0.45, p < 0.01; r = -0.40, p < 0.01). Chi-square analysis indicated a strong association between AQI categories and exacerbation rates (χ² = 25.6, df = 3, p < 0.001). Multiple regression showed that PM10 and NO2 were significant independent predictors of respiratory exacerbation (β = 0.049, p < 0.01; β = 0.038, p < 0.01). Conclusion: The study underscores the adverse respiratory health consequences of poor air quality in Jamshoro and recommends the implementation of effective air quality management policies.

Air Quality Prediction in Urban Environment Using IoT Sensor Data

The increasing concern for environmental health has led to a heightened need for accurate air quality monitoring and prediction. This study presents a framework for predicting the Air Quality Index (AQI) using existing datasets rather than relying on real-time data from IoT sensors. The proposed system incorporates various machine learning algorithms, including Linear Regression, Neural Networks, and XGBoost, to analyze the relationships between air pollution indicators and AQI values. The methodology encompasses essential steps such as data preprocessing, normalization, and dividing the dataset into training and testing sets. Although the system has not yet been implemented, preliminary analyses indicate that the use of these models has the potential to yield reliable AQI predictions, which can significantly assist policymakers and public health officials in implementing effective air quality management strategies.

Decision Support Framework for Water Quality Management in Reservoirs Integrating Artificial Intelligence and Statistical Approaches

Planning, managing and optimising surface water quality is a complex and multifaceted process, influenced by the effects of both climate uncertainties and anthropogenic activities. Developing an innovative and robust decision support framework (DSF) is essential for effective and efficient water quality management, so it can provide essential information on water quality and assist policy makers and water resource managers to identify potential causes of water quality deterioration. This framework is crucial for implementing actions such as infrastructure development, legislative compliance and environmental initiatives. Recent advancements in computational domains have created opportunities for employing artificial intelligence (AI), advanced statistics and mathematical methods for use in improved water quality management. This study proposed a comprehensive conceptual DSF to minimise the adverse effects of extreme weather events and climate change on water quality. The framework utilises machine learning (ML), deep learning (DL), geographical information system (GIS) and advanced statistical and mathematical techniques for water quality management. The foundation of this framework is the outcomes from our three studies, where we examined the application of ML and DL models for predicting water quality index (WQI) in reservoirs, utilising statistical and mathematical methods to find the seasonal trend of rainfall and water quality, exploring the potential connection between streamflow, rainfall and water quality, and employing GIS to show the spatial and temporal variability of hydrological parameters and WQI. Three potable water supply reservoirs in the Toowoomba region of Australia were taken as the study area for practical implementation of the proposed DSF. This framework can serve as a comprehensive mechanism to identify distinct seasonal characteristics and understand correlations between rainfall, streamflow and water quality. This will enable policy makers and water resource managers to enhance their decision making processes by selecting the management priorities to safeguard water quality in the face of future climate variability, including prolonged droughts and flooding.

The Influence of Quality Management Systems on the Success of Information Technology

Regarding the influence of quality management systems on the success of information technology (IT), it can be started by explaining the importance of quality in the development and implementation of IT systems. In the context of modern business, information technology plays a very important role in supporting operations, increasing efficiency, and providing competitive advantage. However, to ensure that IT systems truly support these goals, quality in every aspect of IT development and management must be maintained. This study aims to analyze the influence of quality management systems on the success of information technology. In an increasingly complex business environment, the quality of information technology is a determining factor in achieving organizational goals. An effective quality management system is expected to increase efficiency, reduce risk, and ensure that results are in accordance with predetermined specifications.

Comparative analysis of particle exposure in commuters: Evaluating different modes of transportation in Tehran

Daily commuting significantly contributes to the overall exposure to particulate matter (PM) in urban areas, underscoring the need to understand the factors influencing PM exposure. This study assessed personal exposure levels and inhalation doses of PM2.5, and PM10 across various transportation modes in Tehran, Iran. The study included buses, open-window taxis, subways, walking, and cycling for over 125 trips. Data were collected during the morning and evening peak hours using low-cost sensors, with an average trip distance of 7.50 km. On average, buses exhibited the highest mean PM2.5 concentration (25.0 μgm3), followed by subways (17.0 μgm3), taxis (14.4 μgm3), cycling (13.5 μgm3), and walking (8.80 μgm3). Pearson correlation analysis showed a strong relationship between traffic volume and PM concentrations in taxi and bus modes (r = 0.78 and 0.56, respectively). Subway commuters experienced the lowest PM2.5 inhalation dose (2.50 μg), whereas bus commuters experienced the highest (6.20 μg). Pedestrians had the highest average inhalation dose of PM2.5 with 20.7 μg due to longer trip durations. The daily average PM2.5 levels in all transportation modes exceeded the WHO thresholds by 1.60 times. These findings offer crucial insights into personal exposure concentrations among commuters and serve as a basis for effective air quality management plans and broader global investigations of air pollution.

A Radar-Based Methodology for Aerosol Plume Identification and Characterisation on the South African Highveld

Biomass burning on the South African Highveld annually injects substantial amounts of aerosols and trace gases into the atmosphere, impacting the global radiative balance, cloud microphysics, and regional air quality. These aerosols are transported as plumes over long distances, posing challenges to existing in situ and satellite-based monitoring techniques because of their limited spatial and temporal resolution, particularly in environments with low-level sources. This study aims to develop and validate a novel radar-based methodology to detect, track, and characterise aerosol plumes, addressing the limitations of existing in situ and satellite monitoring techniques. Using high-resolution volumetric reflectivity data from an S-band radar in Pretoria, South Africa, a traditional storm tracking algorithm is adapted to improve plume identification. Case studies of plume events in June and August 2013 demonstrate the radar’s effectiveness in distinguishing lower vertical profiles and reduced reflectivity of plumes compared with storm echoes. The adapted algorithm successfully tracked the spatial and temporal evolution of the plumes, revealing their short-lived nature. Results indicate that radar-derived geospatial characteristics have the potential to contribute significantly to understanding the impacts of plumes on local air quality. These findings underscore the critical need for high spatio-temporal resolution data to support effective air quality management and inform policy development in regions affected by biomass burning.

Explainable artificial intelligence for the interpretation of ensemble learning performance in algal bloom estimation.

Chlorophyll-a (Chl-a) concentrations, a key indicator of algal blooms, were estimated using the XGBoost machine learning model with 23 variables, including water quality and meteorological factors. The model performance was evaluated using three indices: root mean square error (RMSE), RMSE-observation standard deviation ratio (RSR), and Nash-Sutcliffe efficiency. Nine datasets were created by averaging 1hour data to cover time frequencies ranging from 1hour to 1month. The dataset with relatively high observation frequencies (1-24 h) maintained stability, with an RSR ranging between 0.61 and 0.65. However, the model's performance declined significantly for datasets with weekly and monthly intervals. The Shapley value (SHAP) analysis, an explainable artificial intelligence method, was further applied to provide a quantitative understanding of how environmental factors in the watershed impact the model's performance and is also utilized to enhance the practical applicability of the model in the field. The number of input variables for model construction increased sequentially from 1 to 23, starting from the variable with the highest SHAP value to that with the lowest. The model's performance plateaued after considering five or more variables, demonstrating that stable performance could be achieved using only a small number of variables, including relatively easily measured data collected by real-time sensors, such as pH, dissolved oxygen, and turbidity. This result highlights the practicality of employing machine learning models and real-time sensor-based measurements for effective on-site water quality management. PRACTITIONER POINTS: XAI quantifies the effects of environmental factors on algal bloom prediction models The effects of input variable frequency and seasonality were analyzed using XAI XAI analysis on key variables ensures cost-effective model development.