Research Papers - Department of Mechanical Engineering
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/604
Browse
Publication Open Access Aeroacoustic Noise Produced from Novel Wind Turbine Rotor Design for Small-scale Applications in Sri Lanka(SLIIT, 2022-02-11) Perera, M; Bandara, U. HGrowing concerns regarding non-renewable energy sources have driven academic and industrial scholars as well as global superpowers to seek sustainable, greener power generation alternatives. One such prominent renewable substitute is wind power which was initially utilized in harnessing electricity towards the late nineteenth century though archaeological evidence has proved that wind power had been employed for various purposes since predynastic Egypt. Extensive research and development has enabled the efficient operation of multi megawatt wind farms at present though inherent drawbacks still persist, of which aerodynamic noise, also referred to as aeroacoustic noise, is of major concern. This paper details the simulative investigation of the aeroacoustic sound levels produced by an optimized novel wind turbine design intended for the use in small scale applications with medium wind speed conditions in Sri Lanka, using ANSYS Fluent. A transient analysis using the Shear Stress Transport turbulence model was used to obtain the converged pressure fluctuations which subsequently revealed the sound pressure levels via Fast Fourier Transforms at six predetermined locations of interest. The results revealed the presence of acoustic vibrations within the Infrasonic and Low Frequency Noise range with sound pressure levels exceeding one hundred decibels, particularly up to a frequency of twenty five Hertz. Prolonged exposure to elevated levels of low frequency noise has been identified to cause severe discomfort to humans though further conclusive research is required. Finer mesh controls which incorporate minute boundary layer variations during motion and precisely encapsulate the turbine geometry could further improve the accuracy of the results, however this would require adequate computational capacity. The results of this research primarily serve as a basis for identifying possible improvements for the novel rotor design in addition to providing a comparative study for future research, both simulative and empirical, on the aerodynamic noise emissions associated with wind turbines.Publication Embargo Analysis of household cooking energy demand and its environmental impact in Sri Lanka(Pergamon, 2002-11-01) Attalage, R. A; Wijayatunga, Priyantha DCThis paper presents the results and analysis of a study conducted with the objective of investigating the cooking energy requirements in the Sri Lanka domestic sector and the environmental emissions associated with it. The study was conducted out through a sample and showed that the main household energy supply sources were biomass, liquefied petroleum gas (LPG), electricity and kerosene with electricity being used largely for water boiling in all subsectors. It was observed that the urban sector cooking is largely dominated by LPG (95% of urban households) while the rural sector cooking is confined mainly to biomass (95% of rural households). The suburban sector consists of a mixture of all the sources (LPG-70% and biomass-85% of suburban households). Similarly, LPG dominates in electrified households (76.4% of electrified households), while biomass dominates in all non-electrified households. It was found in the analysis that the highest level of gaseous emissions due to cooking activity occurs in the rural areas, mainly due to the relatively large use of biomass, while the lowest level of emissions is recorded in a typical suburban household. Also, the analysis shows that fuel switching in domestic cooking activities from biomass to LPG and kerosene can be used as a measure to reduce emissions due to higher stove efficiencies and lower emission factors associated with these fuels. Substitution of 50% of biomass usage by kerosene in the rural households will result in 39–50% reduction in emissions within the rural sector. Further, substitution of 50% of biomass usage in urban and suburban sectors by LPG results in 4–49% reduction in emissions within these sectors.Publication Embargo Analysis of rural household energy supplies in Sri Lanka: energy efficiency, fuel switching and barriers to expansion(Pergamon, 2003-05-01) Attalage, R. A; Wijayatunga, Priyantha DCA majority of the households in Sri Lanka, as in the case of many developing countries, is concentrated in the rural areas of the country. Unfortunately, very little attention has been paid until recently to analyse and address various issues associated with rural energy supplies, particularly those issues regarding barriers to penetration of clean and convenient sources of energy. This paper presents the results and analysis of a study conducted through a sample study on domestic energy supplies in rural Sri Lanka with emphasis on cooking and lighting energy requirements. The paper has attempted to highlight policy issues associated with rural energy supplies and possible solutions to them in the context of the country’s overall picture of the energy sector.Publication Embargo Analytic hierarchy process for selection of ERP software for manufacturing companies(SAGE Publications, 2008-10) Perera, H. S. C; Costa, W. K. REnterprise Resource Planning (ERP) systems are popular as an IT enabled tool, which integrates different functional areas of business. ERP systems are implemented as a total business solution that supports major functionalities of business. However, many of the implementations are not success stories. Most post implementation problems are due to the inappropriate selection of systems. This paper describes multi-criteria decision model using Analytic Hierarchy Process for the selection of ERP systems for manufacturing companies. First, ERP evaluation criteria are developed by using past literature and through a questionnaire distributed among Sri Lankan manufacturing companies. Seven major criteria are identified and under each criterion several sub-criteria are identified. Selection of the best suited ERP system leads to a multi-criteria decision making problem as ERP systems should be evaluated based upon many criteria. Using the identified main and sub criteria, an Analytic Hierarchy Process (AHP) model is developed for ranking the ERP software. An example of a case is presented to show the actual implementation of AHP model. Expert Choice software is used to solve this AHP model.Publication Open Access Artificial intelligence based smart building automation controller for energy efficiency improvements in existing buildings(2015-08-01) Basnayake, B. A. D.J.C.K; Amarasinghe, Y.W.R; Attalage, R. A; Udayanga, T.D.I; Jayasekara, A.G.B.PThis paper presents the design and implementation details of an Artificial Intelligent based smart building automation controller (AIBSBAC). It has the capability to perform intelligently adaptive to user preferences, which are focused on improved user comfort, safety and enhanced energy performance. The design of AIBSBAC consists of subsystems of smart user identification, internal and external environment observation subsystems, an artificial intelligent decision making subsystem and also a universal infrared communication system. Furthermore, the design architecture of AIBSBAC facilitates quick install flexible plug and play concept for most of the residential and buildings automation applications without a barrier to infrastructure modifications in installation.Publication Embargo An Automated System for Estimating GSM Value of Fabrics using Beta Particle Absorption Characteristics(IEEE, 2021-11-22) Dias, S; Sandaruwan, K. G. D; Jayasekara, SGrams per square meter (GSM) or Grammage is an ISO-recommended term to express the mass per unit area of papers, metal sheets, plastic-made products, and fabric materials. GSM tests are widely used in the textile industry to measure GSM of knitted fabrics, and to ensure quality and other standard fabrics' specifications. Meanwhile, most textile organizations prefer the manual GSM measuring procedure, which leads to many disadvantages, including fabric wastage. An automated non-contact type fabric Grammage measuring method is proposed as an alternative solution for this industrial issue. This paper introduces mathematical models for determining GSM values based on beta particle absorption characteristics of three selected fabrics. Moreover, this study discusses a real-time GSM measuring system, which utilizes the generated mathematical models. Through this paper, developed mathematical models are investigated over the goodness of fit parameters. Developed models are appropriate for GSM value estimation with R2 values over 0.99, and lower Root Mean Square Error (RMSE) Values. Error percentages obtained during the validation of these mathematical models are less than 1% for all fabric types.Publication Embargo Autonomous Cyber AI for Anomaly Detection(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Madhuvantha, K.A.N.; Hussain, M.H.; De Silva, H.W.D.T.; Liyanage, U.I.D.; Rupasinghe, L.; Liyanapathirana, C.Since available signature-based Intrusion Detection systems (IDS) are lacking in performance to identify such cyber threats and defend against novel attacks. It does not have the ability to detect zero-day or advanced malicious activities. To address the issue with signature-based IDS, a possible solution is to adopt anomaly-based detections to identify the latest cyber threats including zero days. We initially focused on network intrusions. This research paper discusses detecting network anomalies using AIbased technologies such as machine learning (ML) and natural language processing (NLP). In the proposed solution, network traffic logs and HTTP traffic data are taken as inputs using a mechanism called beats. Once relevant data has been extracted from the captured traffic, it will be passed to the AI engine to conduct further analysis. Algorithms such as Word2vec, Convolution Neural Network (CNN), Artificial Neural networks (ANN), and autoencoders are used in order to conduct the threat analysis. HTTP DATASET CSIC 2010, that NSL-KDD, CICIDS are the benchmarking datasets used in parallel with the above algorithms in order to receive high accuracy in detection. The outputted data is integrated and visualized using the Kibana dashboard and blockchain model is implemented to maintain and handle all the data.Publication Open Access A Case Study of Technology Transfer Process in a Government Research Organization in Sri Lanka(Technical Reports. Department of Management of Technology, University of Moratuwa Sri Lanka, 2015) Perera, H. S. C; Darshana, M; Liyanage, CThe purpose of this paper is to identify and discuss the critical elements of a successful technology transfer process of a research organization by exploring the technology transfer process adopted by a leading government research institute in Sri Lanka. A field study based on a structured questionnaire and personal interviews was carried out to collect data. The study identified several factors that hinder a successful technology transfer as well as several facilitating factors. Findings reveal that contract research projects and funded projects have the greatest probability of commercialization success. It exposed that only 37% of the technologies that had received patents have been successful in the commercialization stage raising concerns about the research productivity. It was also found that the personal approach to technology transfer is dominating but dwindling compared with other approaches. Although the overall technology transfer success is about 86%, commercialization success is well below an acceptable level for this organization. Finally, this paper presents recommendations for an effective technology transfer process which can be applied for similar institutes.Publication Open Access Challenges and potential impact of applying lean manufacturing techniques to textile knitting industry: A case study of a knitting factory in Sri Lanka(2012) Gamage, K. G. D. A.S; Piyanka, W. P. G. T; Jayathilake, L. P. C. B; Gamage, J. R; Perera, H. S. CApplication of lean manufacturing in mass production, especially in apparel industry, has become a popular practice in meeting the objectives of waste minimization and productivity improvement these days. But when it comes to batch production, for example textile knitting which is an upstream process of the supply chain, application of lean techniques is a challenge. This study investigates challenges of application of lean techniques to a textile knitting factory in Sri Lanka. . The purpose of the study was to investigate the challenges in improving the productivity through lean techniques in a less labour intensive batch production environment. The objectives of the study were to quantify the impact of lean practices and to identify the key challenges specific to the knitting industry. The case study based research approach was followed thought the project which is similar to that used by Kasul and Motwani’s study. Interviews, observations and archival sources were the sources from which data was collected. The results were calculated of main product categories based on the volume and price. For example it was found that the process Value added (VA) to Non-value added (NVA) ratio for JCOL 56(the main product) is 4.64% and with the suggested improvements for waste minimization it was found the ration could be improved to 9.37%. Therefore improving the process would bring in a lot of financial & non-financial gain as well as the lead time reduction which is a key factor in reducing the operational costs.Publication Open Access Classification of failure factors in information systems(2015) Perera, H. S. C; Gunawardhana, D. N. TFailure rate of Information Systems have rapidly increased in different aspects due to different reasons. Although above situation is not a new sight in the field of Information System, it creates many obstacles to regular activities of any organization. The failure of Information System has become a common state for any organization or industry and not depending on their rank or status. Numerous factors may have affected for Information System Failures and these factors are functioning together or individually to create the failure situation of Information Systems. The objective of this paper is to identify the main failure factors in the Information Systems. An in-depth review of the existing literature has been done to meet the objective of this study. Multidisciplinary studies across different countries, industries and areas have taken into account for identifying the main failure factors of Information Systems. This paper is presented to focus the main failure factors that affected for Information System failures based on literature; environment, quality control, human related, technology related and other connected factors. It can be mainly divided into two parts. They are conceptual factors and background factors or hard factors and soft factors. User participation, participant behavior, user satisfaction, attitudes and expectation level, and the management of organization, infrastructure facilities and pattern of usage play a crucial role in the field of Information Systems that have been identified as background factors with significant impact on Information System failures. Quality failure, project failure, system failure, management failure and software failure identified as conceptual failure factors.Publication Embargo Co-production of fucoxanthin, docosahexaenoic acid (DHA) and bioethanol from the marine microalga Tisochrysis lutea(Elsevier, 2021-12-01) Premaratne, M; Liyanaarachchi, V. C; Nimarshana, P. H. V; Ariyadasa, T. U; Malik, A; Attalage, R. AThe marine microalga Tisochrysis lutea is renowned for its ability to synthesize fucoxanthin and docosahexaenoic acid (DHA), which are nutritionally valuable high-value compounds. Although numerous studies in literature have assessed fucoxanthin and DHA production by T. lutea, very few studies have evaluated the feasibility of comprehensively utilizing biomass for co-production of these metabolites within the framework of biorefineries. To this end, the current study focused on the synthesis of fucoxanthin and DHA by cultivation of T. lutea under two different initial nitrate concentrations (1x: 882 µM, 3x: 2,646 µM) and three different light intensities (LL: 50 µmol/m2/s; ML: 100 µmol/m2/s; HL: 150 µmol/m2/s). The maximum fucoxanthin yield of 8.80 ± 0.30 mg/L (14.43 ± 0.52 mg/g) and DHA yield of 7.08 ± 0.02 mg/L (11.90 ± 0.14 mg/g) were achieved in the 3x HL culture at the end of 16 days of cultivation. Thereafter, a novel process of biphasic solvent extraction using ethanol/n-hexane/water (10:9:1 v/v/v) was utilized for co-extraction 97.96 ± 0.54% fucoxanthin and 74.11 ± 1.49% DHA from 3x HL biomass, and products were separated into two fractions. Fermentation of the residual biomass obtained from co-extraction resulted in a bioethanol yield of 48.49 ± 0.58 mg/g. Accordingly, the current study demonstrated the potential of T. lutea as a feedstock for biorefineries.Publication Open Access Comfort conditions for built environments in Sri Lanka(Institution of Engineers, 1999) Jayasinghe, M.T.RThe neutral temperatures for different locations in Sri Lanka have been established using actual climatic data. Based on these neutral temperatures, 'standard comfort zone for each of these locations can be identified on the psychrometric chart. Field measurements have been carried out for the validation of comfort zones for Sri Lankan conditions. The effects of physiological cooling at relatively high internal air velocities have been highlighted. In order to check the applicability of standard modification techniques for the comfort zones to take account of elevated internal air velocities, surveys have been carried out at two different velocities. The need for additional boundaries to standard modifications to suit Sri Lankan conditions have been highlighted. This provides a method of extending the boundaries of these comfort zones thereby accommodating higher levels of dry bulb temperatures and humidites in the built environments. This fact can be utilised as the basis of minimising the energy demand in buildings either air conditioned or not, by making use of combined modes at different internal air velocities.Publication Open Access Comparative assessment on the extraction of carotenoids from microalgal sources: Astaxanthin from H. pluvialis and β-carotene from D. salina(Elsevier, 2019-03-20) Rammuni, M N; Ariyadasa, Thilini U; Nimarshana, P. H. V; Attalage, R. AAstaxanthin and β-carotene are important carotenoids used in numerous pharmaceutical and nutraceutical applications, owing to their vigorous antioxidant properties. The microalgal strains Haematococcus pluvialis and Dunaliella salina accumulate the highest quantities of astaxanthin and β-carotene (up to 7% and 13% dry weight respectively) and are therefore considered as sustainable feedstock for the commercial production of carotenoids. Thus, from an economical perspective, it becomes desirable to optimize recovery of carotenoids from microalgal cells. To this end, here, we have summarized the conventional and modern extraction techniques generally used for the recovery of astaxanthin from Haematococcus pluvialis and β-carotene from Dunaliella salina. Furthermore, we have also discussed the optimum process conditions employed for numerous extraction protocols including solvent extraction, ultrasonic-assisted extraction (UAE), microwave-assisted extraction (MAE) and supercritical fluid extraction (SFE). Overall, our study highlights the sustainability of integrated co-production of biofuels and carotenoids in a biorefinery framework.Publication Open Access Comparing Fuel Consumption and Emission Levels of Hybrid Powertrain Configurations and a Conventional Powertrain in Varied Drive Cycles and Degree of Hybridization(Белорусский национальный технический университет, 2020) Maddumage, W. U; Abeyasighe, K. Y; Perera, M. S. M; Attalage, R; Kelly, PThe use of hybrid electric transmissions in the automotive industry is a solution to the problem of emissions and fuel economy compared to conventional combustion engine vehicles. To achieve the desired results, when designing a hybrid electric vehicle, it is necessary to consider various options, while taking into account fuel consumption and exhaust emissions. The article presents an analysis of the design of an automobile transmission, various options and situations are considered, for example, the target driving cycle and the degree of hybridization. Four transmission configuration models (combustion engine, serial, parallel and complex hybrid transmission configurations) for a small vehicle (motorized three-wheeler) have been developed using Model Advisor software. The listed transmission configurations have been modeled with different driving cycles and varying degrees of hybridization. First, the impact of the vehicle's power management strategy and the performance of various transmission configurations is investigated based on the analysis of exhaust emissions and fuel consumption. Second, driving cycles are scaled according to kinetic intensity and the relationship between fuel consumption and driving cycles is estimated. Thirdly, three fuel consumption models have been developed so that the fuel consumption for an actual driving cycle can be predicted for each transmission configuration. Studies have shown that compared to a conventional transmission, fuel consumption is lower in hybrid vehicles. The tests gave an unexpected result: higher levels of CO emissions from hybrid vehicles. In addition, the fuel consumption of all four transmissions indicates a strong correlation with the kinetic intensity values of the selected driving cycles. It was found that for different driving cycles, the average fuel preference for each cycle was: 23% for sequential, 21% for parallel and 33% for complex hybrids in comparison with the transmission of an internal combustion engine. Experiments have shown that the performance of hybrid configurations varies depending on the driving cycle and degree of hybridization. The article identifies promising areas of research. It was found that for different driving cycles, the average fuel preference for each cycle was: 23% for sequential, 21% for parallel and 33% for complex hybrids in comparison with the transmission of an internal combustion engine. Experiments have shown that the performance of hybrid configurations varies depending on the driving cycle and degree of hybridization. The article identifies promising areas of research. It was found that for different driving cycles, the average fuel preference for each cycle was: 23% for sequential, 21% for parallel and 33% for complex hybrids in comparison with the transmission of an internal combustion engine. Experiments have shown that the performance of hybrid configurations varies depending on the driving cycle and degree of hybridization. The article identifies promising areas of research.Publication Open Access Comparing fuel consumption and emission levels of hybrid powertrain configurations and a conventional powertrain in varied drive cycles and degree of hybridization(Белорусский национальный технический университет, 2020) Maddumage, W. U; Abeyasighe, K. Y; Perera, M. S. M; Attalage, R, A; Kelly, PHybrid electric powertrains in automotive applications aim to improve emissions and fuel economy with respect to conventional internal combustion engine vehicles. Variety of design scenarios need to be addressed in designing a hybrid electric vehicle to achieve desired design objectives such as fuel consumption and exhaust gas emissions. The work in this paper presents an analysis of the design objectives for an automobile powertrain with respect to different design scenarios, i. e. target drive cycle and degree of hybridization. Toward these ends, four powertrain configuration models (i. e. internal combustion engine, series, parallel and complex hybrid powertrain configurations) of a small vehicle (motorized threewheeler) are developed using Model Advisor software and simulated with varied drive cycles and degrees of hybridization. Firstly, the impact of vehicle power control strategy and operational characteristics of the different powertrain configurations are investigated with respect to exhaust gas emissions and fuel consumption. Secondly, the drive cycles are scaled according to kinetic intensity and the relationship between fuel consumption and drive cycles is assessed. Thirdly, three fuel consumption models are developed so that fuel consumption values for a real-world drive cycle may be predicted in regard to each powertrain configuration. The results show that when compared with a conventional powertrain fuel consumption is lower in hybrid vehicles. This work led to the surprisingly result showing higher CO emission levels with hybrid vehicles. Furthermore, fuel consumption of all four powertrains showed a strong correlation with kinetic intensity values of selected drive cycles. It was found that with varied drive cycles the average fuel advantage for each was: series 23 %, parallel 21 %, and complex hybrids 33 %, compared to an IC engine powertrain. The study reveals that performance of hybrid configurations vary significantly with drive cycle and degree of hybridization. The paper also suggests future areas of study.Publication Embargo Component part standardization: A way to reduce the life-cycle costs of products(Elsevier, 1999-04-20) Perera, H. S. C; Nagarur, N; Tabucanon, M. TThis paper studies the effects of component part standardization on life-cycle costs. Three possible situations for component standardization are discussed. A summary is presented of various costs in different phases of the product life cycle and how they are shared among the manufacturer, user, and society. Then, we explain how the component standardization reduces the costs of different phases of the product life cycle. Finally, we point out some of the possible disadvantages of component standardization.Publication Embargo Comprehensive Analysis of Convolutional Neural Network Models for Non-Instructive Load Monitoring(IEEE, 2020-10-20) Herath, G. M; Thilakanayake, T. D; Liyanage, M. H; Angammana, C. JNon-Instructive Load Monitoring (NILM) schemes have become more popular in recent years with the availability of smart meters. It provides energy use data to utilities and per-appliance energy consumption details to end users. This study carries out a comprehensive analysis of existing Convolutional Neural Network (CNN) architectures that have been used for NILM. Nevertheless, it provides an unbiased comparison of the existing architectures thereby helping to select the best performing model for NILM applications. The commonly used CNN disaggregation models were categorized into distinctive groups based on their architectures which considered structure of the Neural Network (NN) and outputs. It considers regression-based sequence to sequence and sequence to point mapping, classification-based sequence to point hard association and soft association-based mapping. The CNN models are improved and modified to bring them onto a common platform for comparison. Thereafter, a rigorous comparison was performed using indices which included accuracy, precision, F-measure and recall. The results reveal interesting relationships between architectures, appliances and measures.Publication Embargo Converting existing Internal Combustion Generator (ICG) systems into HESs in standalone applications(Pergamon, 2013-10-01) Perera, A.T. D; Attalage, R. A; Perera, K.K.C.K; Dassanayake, V. P. CExpanding existing Internal Combustion Generator (ICG) systems by combining renewable energy sources is getting popular due to global concern on emission of green house gases (GHG) and increasing fossil fuel costs. Life cycle cost, initial capital cost (ICC), power supply reliability of the system, and GHG emission by ICG are factors to be considered in this process. Pareto front of Levelized Energy Cost (LEC)–Unmet Load Fraction (ULF)–GHG emission was taken in this study for four different expansion scenarios. Furthermore, Pareto front of ICC–LE–ULF was taken for three different expansion scenarios in order to analyze the impact of renewable energy integration. The results clearly depict that characteristics of the Pareto front varies with the scale of expansion and objectives taken for the optimization. A detailed analysis was conducted for a scale up problem with a 4 kVA ICG by using the Pareto fronts obtained.Publication Open Access A Cost Model for Evaluating Component Standardisation: A Case Study(O. P. A, 2000) Nagarur, N. N; Perera, H. S. C; Tabucanon, M. TAs manufacturing industry tries to grapple the oftenconflicting objectives of increasing product variety and reducing the production costs, one of the strategies oft contemplated is component standardization or using common components. However, developing and using standard components may sometimes push the overall costs actually higher. This paper proposes an evaluation model for decision making in the context of component standardization. First, it discusses various types of costs to be considered for selecting desired components. Then the paper presents a specific case study in which some purchasing parts are considered for standardization. An evaluation model is developed for the relevant costs of the case. The solution and sensitivity analysis are presented and discussed.Publication Open Access Deep Machine Learning-Based Water Level Prediction Model for Colombo Flood Detention Area(MDPI, 2023-02-08) Herath, M; Jayathilaka, T; Hoshino, Y; Rathnayake, UMachine learning has already been proven as a powerful state-of-the-art technique for many non-linear applications, including environmental changes and climate predictions. Wetlands are among some of the most challenging and complex ecosystems for water level predictions. Wetland water level prediction is vital, as wetlands have their own permissible water levels. Exceeding these water levels can cause flooding and other severe environmental damage. On the other hand, the biodiversity of the wetlands is threatened by the sudden fluctuation of water levels. Hence, early prediction of water levels benefits in mitigating most of such environmental damage. However, monitoring and predicting the water levels in wetlands worldwide have been limited owing to various constraints. This study presents the first-ever application of deep machine-learning techniques (deep neural networks) to predict the water level in an urban wetland in Sri Lanka located in its capital. Moreover, for the first time in water level prediction, it investigates two types of relationships: the traditional relationship between water levels and environmental factors, including temperature, humidity, wind speed, and evaporation, and the temporal relationship between daily water levels. Two types of low load artificial neural networks (ANNs) were developed and employed to analyze two relationships which are feed forward neural networks (FFNN) and long short-term memory (LSTM) neural networks, to conduct the comparison on an unbiased common ground. The LSTM has outperformed FFNN and confirmed that the temporal relationship is much more robust in predicting wetland water levels than the traditional relationship. Further, the study identified interesting relationships between prediction accuracy, data volume, ANN type, and degree of information extraction embedded in wetland data. The LSTM neural networks (NN) has achieved substantial performance, including R2 of 0.8786, mean squared error (MSE) of 0.0004, and mean absolute error (MAE) of 0.0155 compared to existing studies.