Environmental Monitoring and Assessment最新文献

{"title":"Integrating machine learning and remote sensing for long-term monitoring of chlorophyll-a in Chilika Lagoon, India","authors":"Hafez Ahmad,&nbsp;Padmanava Dash,&nbsp;Rajendra M. Panda,&nbsp;Pradipta R. Muduli","doi":"10.1007/s10661-024-13463-8","DOIUrl":"10.1007/s10661-024-13463-8","url":null,"abstract":"<div><p>Chlorophyll-a (Chla) is recognized as a key indicator of water quality and ecological health in aquatic ecosystems, offering valuable insights into ecosystem dynamics and changes over time. This study aimed to to develop and validate a robust ML model for estimating Chla using Landsat data, produce a time series of Chl a maps, and analyze the spatiotemporal variability of Chla in Chilika Lagoon, Asia’s largest brackish water lagoon. Nine ML regression models, including Extreme Gradient Boost, Support Vector Regression, Random Forest, and Bagging Regression, were evaluated using Landsat imagery and field data. After extensive hyperparameter tuning, the Bagging Regression model achieved the highest estimation accuracy, with an R² of 0.8776 and a Root Mean Square Error of 0.9190 µg/L. This optimized model was subsequently applied to generate a time series of Chla maps for Chilika Lagoon from 2014 to 2023, revealing notable seasonal and spatial variability. Chla concentrations peaked during summer months and were generally higher in the lagoon’s northwestern region, gradually decreasing towards the southern area. This approach holds promise for precise Chla monitoring in diverse lagoon environments and may aid in the assessment and management of similar coastal and inland lake ecosystems worldwide.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Soil temperature estimation at different depths using machine learning paradigms based on meteorological data","authors":"Anurag Malik,&nbsp;Gadug Sudhamsu,&nbsp;Manjinder Kaur Wratch,&nbsp;Sandeep Singh,&nbsp;Srinadh Raju Sagiraju,&nbsp;Lamjed Mansour,&nbsp;Priya Rai,&nbsp;Rawshan Ali,&nbsp;Alban Kuriqi,&nbsp;Krishna Kumar Yadav","doi":"10.1007/s10661-024-13497-y","DOIUrl":"10.1007/s10661-024-13497-y","url":null,"abstract":"<div><p> Knowledge of soil temperature (ST) is important for analysing environmental conditions and climate change. Moreover, ST is a vital element of soil that impacts crop growth as well as the germination of the seeds. In this study, four machine-learning (ML) paradigms including random forest (RF), radial basis neural network (RBNN), multi-layer perceptron neural network (MLPNN), and co-active neuro-fuzzy inference system (CANFIS) were used for estimation of daily ST at different soil depths (i.e. 5 cm: ST₅; 15 cm: ST₁₅; and 30 cm: ST₃₀) during 2016–2019 at Bathinda weather station, located in South-western Punjab (India). Five different combinations were formulated using four meteorological data, namely <i>T</i>_mean (mean air temperature), RH (relative humidity), WS (wind speed), and SSH (bright sunshine hours), and the optimal one was nominated by employing the gamma test (GT) for each soil depths, respectively. During the validation period, the outcomes of the RF, RBNN, MLPNN, and CANFIS models were evaluated according to performance metrics such as mean absolute error (MAE), root mean square error (RMSE), scatter index (SI), coefficient of efficiency (COE), Pearson correlation coefficient (PCC), and index of agreement (IOA), as well as through pictorial interpretation (Taylor diagram, box-whisker plots, time-variation, scatter plot, and radar chart). The comparison of the results of ML paradigms revealed the highest accuracy was achieved by the CANFIS model at all depths with MAE (RMSE) = 0.788, 0.636, 0.806 (1.074, 0.854, 1.041) °C, SI = 0.040, 0.033, 0.040, and COE (PCC)/IOA = 0.986, 0.991, 0.985 (0.994, 0.995, 0.993)/0.996, 0.998, 0.996. Thus, the results highlight the capability of the CANFIS model with <i>T</i>_mean, RH, WS, and SSH inputs for daily ST estimation at different soil depths on the study site.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Local inventories for effective management of alien species: insights from the alien flora of Jammu, Kashmir, and Ladakh, India","authors":"Shabir A. Zargar,&nbsp;Zafar A. Reshi,&nbsp;Aijaz H. Ganie,&nbsp;Harish Chander Dutt,&nbsp;Manzoor A. Shah,&nbsp;Namrata Sharma","doi":"10.1007/s10661-024-13479-0","DOIUrl":"10.1007/s10661-024-13479-0","url":null,"abstract":"<div><p>The broad-scale inventories of alien species reveal macroecological patterns, but these often fall short in guiding local-level management strategies. Local authorities, tasked with on-the-ground management, require precise knowledge of the occurrence of invasive species tailored to their jurisdictional boundaries. What proves critical at the local scale may not hold the same significance at national or regional levels. In this context, we present a comprehensive inventory of alien vascular plant species across the ecologically diverse Jammu, Kashmir, and Ladakh (JKL) regions of India. Our study identifies 312 alien plant species belonging to 210 genera and 61 families. These alien plant species are predominantly herbaceous dicots. Of these, <i>ca.</i> 62% are naturalized, and 28% exhibit invasive behavior in the region. Introductions have been primarily unintentional, with a notable fraction (26%) introduced for ornamental purposes. The families with the highest number of alien plant species are Asteraceae (46 species), Fabaceae (28 species), and Amaranthaceae (23 species). The genera with the most species are <i>Amaranthus</i> (10 species), <i>Solanum</i> (8 species), <i>Iris</i> (7 species), and <i>Oenothera</i> (5 species). The Jammu region has the highest number of alien plant species, with 221 documented species, including 99 unique to this region. This is followed by the Kashmir Himalaya, with 212 alien species, 70 of which are exclusive to the area. In Ladakh, 76 alien species are recorded, with only one exclusive to the region. Fifty-five alien species are common across all three regions. In each region, more than 50% of species are naturalized, while invasive species constitute about 30% of the total. Therophytes are the dominant life-form category across all regions. Only 18% of species are shared across the three regions. Our findings emphasize the imperative of integrating local-scale knowledge into invasion management frameworks, ensuring targeted and effective strategies aligned with local administrative capacities. By bridging the gap between broad ecological patterns and localized management needs, our study advocates for a nuanced approach to invasive species management that accounts for regional and local specificity.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping of high-resolution daily particulate matter (PM2.5) concentration at the city level through a machine learning-based downscaling approach","authors":"Phuong D. M. Nguyen,&nbsp;An H. Phan,&nbsp;Truong X. Ngo,&nbsp;Bang Q. Ho,&nbsp;Tran Vu Pham,&nbsp;Thanh T. N. Nguyen","doi":"10.1007/s10661-024-13562-6","DOIUrl":"10.1007/s10661-024-13562-6","url":null,"abstract":"<p>PM_2.5 pollution is a major global concern, especially in Vietnam, due to its harmful effects on health and the environment. Monitoring local PM_2.5 levels is crucial for assessing air quality. However, Vietnam’s state-of-the-art (SOTA) dataset with a 3 km resolution needs to be revised to depict spatial variation in smaller regions accurately. In this research, we investigated machine learning-based downscaling methods to improve the spatial resolution and quality of Vietnam’s existing 3 km PM_2.5 products using different approaches: traditional machine learning models (random forest, XGBoost, Catboost, support vector regression (SVR), mixed effect model (MEM)) and deep learning models (long short-term memory (LSTM), convolutional neural network (CNN), convolutional LSTM (ConvLSTM)). Overall, the CatBoost 2-day lag model exhibited superior performance. In terms of modeling, integrating temporal factors into tree-based models can enhance predictive accuracy. Furthermore, when faced with small datasets, traditional machine learning models demonstrate superior performance over complex deep learning approaches. The validation of machine and deep learning models based on their PM_2.5 generated maps is requested because these models can obtain very high results for model evaluation but are unrealistic for application. In this study, compared to the state-of-the-art (SOTA) PM_2.5 maps in Vietnam and the SOTA global maps, the proposed CatBoost 2-day lag model’s maps showed a 57% increase in the correlation coefficient (Pearson R), as well as 42–73%, 28–75%, and 39–75% reductions in root mean squared error (RMSE), mean relative error (MRE), and mean absolute error (MAE), respectively. Additionally, the daily, monthly, and year-average maps generated by the Catboost 2-day lag model effectively capture the spatial distribution and seasonal variations of PM_2.5 in Ho Chi Minh City. These findings indicate a substantial enhancement in the accuracy and reliability of downscaled PM_2.5 maps.</p>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comprehensive review on advanced trends in treatment technologies for removal of Bisphenol A from aquatic media","authors":"Sangeen Waleed,&nbsp;Muhammad Haroon,&nbsp;Naeem Ullah,&nbsp;Mustafa Tuzen,&nbsp;Imran Khan Rind,&nbsp;Ahmet Sarı","doi":"10.1007/s10661-024-13460-x","DOIUrl":"10.1007/s10661-024-13460-x","url":null,"abstract":"<div><p>Toxic environmental pollutants are considered to be posed a major threat to human and aquatic systems. The fast advancement of the petrochemical and chemical industries has woken up rising worries concerning the pollution of water by contaminants including phenolic Bisphenol A (BPA), an endocrine-disrupting chemical (EDC). The intermediate BPA used in synthesis of certain plastics, polycarbonate polymers, polysulfone, and epoxy resins of various polyesters. Due to potential health risks, severe toxicity, and widespread distribution, there is an urgent need to develop efficient techniques for the removal of BPA. Therefore, advance management for the active elimination of BPA prior to its release into the water sources is of serious concern. Degradation, membrane separation, adsorption, and biological treatments have been extensively examined as they are easy to operate and cost-effective for effective BPA removal. In this review, we summarized the mechanism and performance for removal of BPA by several sorbents, including natural polymers, natural inorganic minerals, porous and carbon-based materials. Comparative results revealed that composite materials and modified adsorbents have good performances for removal of BPA. Furthermore, kinetic study investigating adsorption mechanisms was also discussed. Hazardous quantities of such types of chemicals in various samples have thus been the subject of increasing concern of investigation. This review clarified the extensive literature regarding the major health effects of BPA and its advanced treatment technologies including biological treatment by natural and synthetic materials have been discussed briefly. It delivers regulation for future development and research from the aspects of materials functionalization, development of methods, and mechanism investigation that directing to stimulate developments for removal of emerging contaminants.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study on the synergistic mechanism of proline in the treatment of high-salt phenolic wastewater by short-time aerobic digestion process","authors":"Yongqiang Zhu,&nbsp;Yaoqiang Huo,&nbsp;Minli Zhang,&nbsp;Zhiling Li,&nbsp;Yujun Huang","doi":"10.1007/s10661-024-13552-8","DOIUrl":"10.1007/s10661-024-13552-8","url":null,"abstract":"<div><p>High salt concentrations pose a significant challenge to the efficiency of activated sludge (AS) in phenolic wastewater treatment. As a cellular osmoprotectant, proline (Pro) has the capacity to increase the salt tolerance of microbes in AS, hence improving the efficiency of phenolic wastewater degradation. Nevertheless, the precise mechanism behind this enhancement remains ambiguous. This study utilized short-time aerobic digestion (STAD) to examine the kinetics of phenol degradation (250–750 mg/L) by AS under high-salinity stress (2–8%), with the inclusion of Pro (115–575 mg/L) as an auxiliary agent. The process was optimized via response surface methodology (RSM), and the mitigating effect of Pro on microorganisms in AS subjected to salt stress was evaluated. The results demonstrated that the addition of 468 mg/L Pro substantially improved the ability of AS to withstand high-salinity wastewater with high phenol concentrations, which had a salinity of 5.1% and a phenol concentration of 531 mg/L. The addition led to a mitigation rate of the phenol degradation constant <i>k</i>₀ of 38.59 ± 1.54%, resulting in enhanced degradation of chemical oxygen demand (COD), NH₄⁺-N, and NO₃⁻-N. In addition, the prolonged presence of Pro increased AS dehydrogenase activity (DHA) by 24.82% after 30 days. Microbial community analysis demonstrated that Pro promoted the proliferation of functional microorganisms such as Proteobacteria, Firmicutes, <i>Acinetobacter</i>, and <i>Comamonas</i>. These bacteria have essential functions in the elimination of phenol and organic matter, as well as the absorption of nitrogen. This study emphasizes the impact of Pro as a compatible solute in the treatment of high-salinity and high-phenol wastewater in the STAD process.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The older, the better: a comprehensive survey of soil organic carbon under commercial oil palm plantations","authors":"Karolina Golicz,&nbsp;Sim Choon Cheak,&nbsp;Suzanne Jacobs,&nbsp;André Große-Stoltenberg,&nbsp;Mojdeh Safaei,&nbsp;Sonoko Bellingrath-Kimura,&nbsp;Lutz Breuer,&nbsp;Ariani Wartenberg","doi":"10.1007/s10661-024-13540-y","DOIUrl":"10.1007/s10661-024-13540-y","url":null,"abstract":"<div><p>Soil conditions of croplands are a frequent topic of scientific research. In contrast, less is known about large-scale commercial plantations of perennial crops such as oil palm. Oil palm is a globally important tropical commodity crop which contributes to both food and energy security due to its exceptional productivity. However, oil palm crops are associated with short lifecycles and high nutrient demands, which may disproportionately affect soil health. With the goal of exploring baseline soil properties in commercial oil palm plantations, we evaluated data from two large-scale soil surveys carried out in 2014/2015 and 2018/2019 across more than 400 fields located throughout Peninsular Malaysia. We examined variation in field-measured soil quality indicators with a focus on soil organic carbon content at three depths (0–15 cm, 15–30 cm, 30–45 cm) and investigated links with spatial covariates, including plantation age. We found SOC contents to be low (1.6–2%) across the sampled locations with limited correlation with spatial predictors employed in soil organic carbon modelling. Furthermore, we found that immature and young mature plantations, which consisted of fields that were re-planted as part of a 20-year-long oil palm rotation, were characterised by significantly lower soil organic carbon content than the mature plantations. This suggests that management practices should target younger oil palm plantations for soil organic conservation measures to increase the overall baseline SOC content, which will subsequently accumulate over the plantation’s lifespan. We further provide recommendations for future soil sampling efforts, which could increase the robustness of collected data and facilitate their use for soil monitoring through modelling approaches involving, for example, digital soil mapping.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10661-024-13540-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feasibility of UAV photogrammetry for shoreline profile changes on critical beach area: a case study at Pantai Mengabang Telipot","authors":"Muhammad Najmi Kamarudin,&nbsp;Khairul Nizam Tahar","doi":"10.1007/s10661-024-13588-w","DOIUrl":"10.1007/s10661-024-13588-w","url":null,"abstract":"<div><p>This study evaluates the effectiveness of unmanned aerial vehicles (UAVs) in monitoring coastal changes at Pantai Mengabang Telipot, Kuala Terengganu, Malaysia. Addressing the limitations of traditional monitoring methods, such as ground-based surveys and satellite imagery, the research underscores the critical need for timely and precise coastal monitoring using drone technology. The study employs a comprehensive four-phase methodology involving area identification, data acquisition through UAV imagery, data processing, and accuracy analysis. The orthophoto accuracy achieved, compared to detailed shoreline surveys, is 0.064 m. Analysis of shoreline changes over two observation periods reveals a retreat of 0.056 m per day over 14 days, escalating to 0.180 m per day during the subsequent 20 days. These findings highlight the influence of the Southwest Monsoon and man-made structures on coastal dynamics. The results contribute significantly to advancing UAV-based coastal change assessments, emphasizing their pivotal role in precision-driven decision-making for sustainable coastal management.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artisanal and small-scale limestone mining affects soil parameters in Sohra (Meghalaya), India","authors":"R. Eugene Lamare,&nbsp;O. P. Singh","doi":"10.1007/s10661-024-13573-3","DOIUrl":"10.1007/s10661-024-13573-3","url":null,"abstract":"<div><p>In this study, we assessed the changes in the physical and chemical characteristics of the soil samples collected from the artisanal and small-scale limestone mining site in Sohra (Cherrapunjee), Meghalaya, by comparing them with the non-mining site. Eleven distinct soil parameters, namely pH, electrical conductivity (EC), texture (ST), moisture content (MC), bulk density (BD), total porosity (TP), water holding capacity (WHC), organic carbon (OC), total nitrogen (TN), available phosphorus (AP), and exchangeable potassium (EK), were evaluated seasonally (winter, pre-monsoon, and post-monsoon) for 2 years. The results showed that limestone mining has significantly affected the soil quality. The effect is evident by the substantial increases in EC values, sand content, and alkaline soils coupled with noticeably low concentrations of OC and TN. In addition, prominent changes were perceived in the soil MC and EK content, as well as in WHC, BD, and TP percent. Results from ANOVA revealed significant differences (<i>p</i> &lt; 0.05) in mean values at different sampling seasons and sites. The multivariate statistical analysis results showed that the computed correlation coefficient (<i>r</i>) matrix data ranged from − 1.00 to 0.974. A strong positive correlation was highest between OC and TN (0.974), followed by OC with EK (0.828). Principal component (PC) analysis revealed two major components, PC 1 and PC 2, having eigenvalues of 6.276 and 1.747, respectively. Cumulatively, these two components explained 80.23% of the total variance. The loading factor in PC 1 is high and is attributed to OC (.974), TN (.970), and EK (.903). However, in PC 2, the loading factor is positively pooled by MC (0.894) and TP (0.765). The present study concludes that artisanal and small-scale limestone mining altered the soil’s physical and chemical properties, and these changes are likely to have a subsequent deteriorating impact on the area’s biodiversity, landscape, and natural ecosystem. Therefore, to minimize the impact and ensure sustainable soil management in the area, approaches for effective mitigation and remediation measures, including formulating steps for the conservation and enhancement of the soil’s environmental quality, are recommended.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the accuracy of various statistical models for forecasting PM(_{2.5}): a case study from diverse regions of Gandhinagar and Ahmedabad","authors":"Sajeed I. Ghanchi,&nbsp;Dishant M. Pandya,&nbsp;Manan Shah","doi":"10.1007/s10661-024-13550-w","DOIUrl":"10.1007/s10661-024-13550-w","url":null,"abstract":"<div><p>PM<span>(_{2.5})</span> is the most hazardous air pollutant due to its smaller size, which allows deeper bodily penetration. Three diverse regions from Gujarat, India, namely Sector 10, Maninagar, and Vatva, which have green space, high population concentration, and industries, respectively, were chosen to forecast PM<span>(_{2.5})</span> concentration for the next day. Four statistical models, including Multiple Linear Regression (MLR), Principal Component Regression (PCR), Simple Exponential Smoothing (SES), and Autoregressive Integrated Moving Average (ARIMA), were chosen to forecast PM<span>(_{2.5})</span> levels. For this study, data of various pollutants and meteorological parameters were collected from February 2019 to September 2023. Analysis of the seasonal patterns of PM<span>(_{2.5})</span> revealed elevated concentrations during post-monsoon and winter, in contrast to reduced levels during summer and monsoon. Statistical analysis revealed that the concentration of PM<span>(_{2.5})</span> in Sector 10 is much lower than in the other two regions. The analysis of the test results, utilising various accuracy measures like RMSE, MAE, MAPE, IA, and others, indicated that Sector 10 achieved the highest precision in its results. While assessing the models’ accuracy on the test data, the ARIMA model demonstrated the highest level of precision. The average RMSE, MAE, and MAPE values for the ARIMA model were 12.63, 8.59, and 0.24, respectively. In the comparison of the performance between these statistical models and the neural network-based Multilayer Perceptron (MLP) model, it was observed that the statistical model demonstrated superior performance over the MLP model.</p></div>","PeriodicalId":544,"journal":{"name":"Environmental Monitoring and Assessment","volume":"197 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}