Kelantan River Research Articles

Assessing The Impact of Lithological and Geological Features on Electrical Resistivity Tomography (ERT) at Kelantan River Basin, Malaysia

The relationship between lithological and geological features, as assessed through Electrical Resistivity Tomography (ERT), is crucial for exploring subsurface characteristics. ERT is non-invasive and provides high-resolution images of subsurface electrical resistivity, closely linked to lithologyand geological formations. This study aims to accurately delineate lithology, geological formations, and aquifer presence, whether in alluvial layers or bedrock. ERT measurements, employing Pole-dipole and Gradient-XL protocols, were conducted at At-Taqwa Mosque in Gua Musang, Mini Zoo in Kuala Krai, Kampung Sedar, and Kuala Jambu in Tumpat, Kelantan. Results indicated regions with high clay content exhibited low electrical resistivity (<100Ωm), whereas areas with sand and gravel deposits showed high resistivity (>500Ωm). Faults and fractures within hard layers significantly influenced resistivity values, revealing intricate connections between survey lines. Algorithmic analysis integrated with topographical data enhanced the identification of mineral exploration potential, paving the way for real-time monitoring. The Kelantan River Basin was selected due to its environmental importance, facilitating insights into groundwater dynamics, economic significance, and sustainable development practices. This study underscores ERT's role in ground management strategies, mineral exploration, and advancing ground exploration technologies.

Geneticizing input selection based advanced neural network model for sediment prediction in different climate zone

The study focuses on developing an accurate prediction model for suspended sediment load (SSL) based on antecedent SSL and water discharge values. Two Artificial Intelligence (AI) models, Hybrid and Parallel, were employed to test on the Kelantan and Mississippi Rivers in different climate zones and river sizes. The parallel model showed better performance than the hybrid in most cases, with the best results based on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) (432.06 and 782.15 respectively) for Kelantan and (31672.25 and 62356.60 respectively) for Mississippi. The multifunctional GA neural-network model results have proven its ability to predict SSL in tropical and semi-arid zones. In the Kelantan River, the 8-input combination set was the best prediction model, showing an improvement of more than 38% compared to traditional models. The proposed method has proven to be more accurate than traditional models, ensuring better water resource planning, agricultural management and reservoir operation.

Hybrid machine learning model based on feature decomposition and entropy optimization for higher accuracy flood forecasting

The advancement of machine learning model has widely been adopted to provide flood forecast. However, the model must deal with the challenges to determine the most important features to be used in in flood forecast with high-dimensional non-linear time series when involving data from various stations. Decomposition of time-series data such as empirical mode decomposition, ensemble empirical mode decomposition and discrete wavelet transform are widely used for optimization of input; however, they have been done for single dimension time-series data which are unable to determine relationships between data in high dimensional time series. In this study, hybrid machine learning models are developed based on this feature decomposition to forecast the monthly water level using monthly rainfall data. Rainfall data from eight stations in Kelantan River Basin are used in the hybrid model. To effectively select the best rainfall data from the multi-stations that provide higher accuracy, these rainfall data are analyzed with entropy called Mutual Information that measure the uncertainty of random variables from various stations. Mutual Information act as optimization method helps the researcher to select the appropriate features to score higher accuracy of the model. The experimental evaluations proved that the hybrid machine learning model based on the feature decomposition and ranked by Mutual Information can increase the accuracy of water level forecasting. This outcome will help the authorities in managing the risk of flood and helping people in the evacuation process as an early warning can be assigned and disseminate to the citizen.

Multi-isotopic and hydrochemical evidence of water resources evolution and recharge estimation in the tropical coastal aquifer

The study integrates hydrochemical and isotopic (δ18O, δ2H, 3H, and δ13C) techniques to investigate water evolution in the North Kelantan River basin. Groundwater facies were mainly classified as Ca–Mg–Cl, Ca–Mg–Cl–HCO3, and Na–Cl during the rainy season and shift toward Ca–Mg–HCO3 and Na–Ca–HCO3–Cl during the dry season in surface water and shallow aquifer, while facies in intermediate and deep aquifers were classified as Na–HCO3 and Na–Cl. The δ18O and δ2H compositions of most groundwater samples have not deviated significantly from NKMWL (δ2H = 8.4 δ18O + 11.5) with slightly depleted isotopic values due to the humid climate. Isotopically, evaporation does not impact recharged water significantly. However, shallow aquifers are slightly enriched than deep aquifers of the study area. The estimated recharge was 20.17% and 22.52% of annual rainfall based on the CMB and δ18O values, respectively. The recharge mainly occurs during the wet season and is influenced mostly by the amount of rain. Aquifers clustered in distinct groups based on their isotopic signatures and hydrochemical results. The decomposition of organic matter is the primary carbon source in the study area. Building on this, by utilizing isotope hydrology to study water resources, we can gain a deeper insight into the susceptibility of groundwater in coastal aquifers of monsoonal tropical humid regions.

Assessment Of Rainfall Pattern And Future Change For Kelantan River Basin, Malaysia Using Statistically Downscaled Local Climate Models

<p>Climate change has been discussed frequently in recent decades, and it has increased the probability of extreme flood occurrence. This study aims to provide an analysis of future rainfall patterns and flood occurrences specifically for the Kelantan River Basin which is identified as one of flood prone areas in Malaysia. The study area was divided into five regions of the Kelantan River Basin, - Kota Bharu (Northern), Kuala Krai (Center), Pos Lebir (Southeastern), Pos Hua (Southwestern) and Pos Gob (Northwestern). The historical rainfall data (1986-2019) was then retrieved from the Malaysian Meteorological Department (MMD) based on the five regions. The statistical approach was applied to downscaled climate model data from the CanESM2 GCM forced by the Representative Concentration Pathway (RCP) 4.5 and 8.5. The reliability assessment using a Cronbach’s Alpha, Linear Regression and Pearson Correlation results show that local climates (2006-2019) forced by RCP4.5 have a similar trend to historical rainfall within the same period. The spatial analysis outcomes showed that the northeastern region of the Kelantan River Basin received its highest average annual rainfall (5,000 mm) in 1990 and caused severe flooding in the area. However, there is a significant change of rainfall pattern in all regions, with a steady increase in annual rainfall in the southwestern region (2021-2100).</p>

Evaluation of NASA POWER and ERA5-Land for estimating tropical precipitation and temperature extremes

Long-term gridded climate data, NASA Prediction of Worldwide Energy Resources (NASA POWER) and the fifth generation of European ReAnalysis Land Component (ERA5-Land), are important alternatives to gauges, but their effectiveness in capturing tropical precipitation and temperature extremes has not been thoroughly studied. Therefore, this study aims to evaluate the performance of NASA POWER and ERA5-Land over the Kelantan River Basin from 1981 to 2020 with 19 gauges in the aspects of climatology characteristics, overall assessment, precipitation detection capability, probability distribution function (PDF), extreme indices calculation, and the 2014–2015 flood. The important findings are as follows: (1) NASA POWER and ERA5-Land are able to reasonably capture the climatology patterns of precipitation, maximum, and minimum temperatures, with the latter performing slightly better; (2) Both products have a better correlation with gauges over coastal regions than inland mountainous regions, but they tend to underestimate precipitation and maximum temperature and overestimate minimum temperature; (3) With high POD values and moderate FAR and CSI values, they are able to detect precipitation days more effectively than non-precipitation days; (4) The PDF assessment reveals that both products overestimate moderate precipitation (1–20 mm/day) and underestimate no/tiny (0–1 mm/day), heavy (20–50 mm/day), and violent (greater than50 mm/day) precipitation; (5) With the exception of CWD and R10mm, both products tend to significantly underestimate most of the precipitation extreme indices, while a better correlation with gauges can be found in the calculations of CDD, R10mm, R20mm, TXx, and TNn; (6) Both products have a higher correlation and a better precipitation detection ability during the 2014–2015 flood, but they significantly underestimate the amount of precipitation. The findings show that NASA POWER and ERA5-Land offer valuable climate information for locations without gauges, but it is recommended to apply bias correction prior to applying them in this tropical basin.

Unravelling Spatial-temporal Evolution of Shoreline Changes in Pantai Mek Mas – Pantai Cahaya Bulan, Kelantan, Malaysia

Kelantan is a state on Peninsular Malaysia’s East Coast famed for its tropical jungle and seaside areas. Kelantan is a “flood-state” that encounters monsoons and tidal currents. Kelantan was devastated by tsunami-like floods in 2014 where it brought changes on its coastal geomorphology. Using a universal Digital Shoreline Analysis System (DSAS) technique, this study assesses shoreline changes along Kelantan’s coastline between 2013 (before the catastrophic flood) and 2021. A multipronged approach incorporating DSAS via GIS and satellite imagery were used to explore the coastline changes in Kelantan. This study found that Pantai Mek Mas and Pantai Kundur were the most sedimented and the most eroded area were around Pantai Cahaya Bulan, Kota Bharu respectively. The Shoreline Change Envelope (SCE) and Net Shoreline Movement (NSM) analysis concluded that the coastal area has the highest accretion rate of 177.07m/year and the greatest negative distance via NSM of -171.53m/year. The sedimentation along Pantai Mek Mas may happen due to the transportation of sedimentation via river flows from Kelantan River estuary and the degradation of shoreline along Pantai Cahaya Bulan may cause by the concentration of anthropogenic interventions. In conclusion, can be seen that the Kelantan’s coastal area shoreline does progressively proliferate over the past decade and the community vulnerability on the shoreline changes are at risk which comprehensive mitigation is needed to improve its resilience.

Assessment of Three GPM IMERG Products for GIS-Based Tropical Flood Hazard Mapping Using Analytical Hierarchy Process

The use of satellite precipitation products can overcome the limitations of rain gauges in flood hazard mapping for mitigation purposes. Hence, this study aims to evaluate the capabilities of three global precipitation measurement (GPM) integrated multisatellite retrievals for GPM (IMERG) products in tropical flood hazard mapping in the Kelantan River Basin (KRB), Malaysia, using the GIS-based analytic hierarchy process (AHP) method. In addition to the precipitation factor, another eleven factors that contribute to flooding in the KRB were included in the AHP method. The findings demonstrated that the spatial pattern and percentage area affected by floods simulated under the IMERG-Early (IMERG-E), IMERG-Late (IMERG-L), and IMERG-Final (IMERG-F) products did not differ significantly. The receiver operating characteristics curve analysis showed that all three IMERG products performed well in generating flood hazard maps, with area under the curve values greater than 0.8. Almost all the recorded historical floods were placed in the moderate-to-very-high flood hazard areas, with only 1–2% found in the low flood hazard areas. The middle and lower parts of the KRB were identified as regions of “very high” and “high” hazard levels that require particular attention from local stakeholders.

Determination of Silt and Clay soil particle distribution using new Silt-Clay Separation Quick method

Hydrometer method is the standard method that normally used to determine fine particle size distributions for soil classification purposes. This study aims to develop new method that enable quick determination of silt-clay particle distribution compared to the hydrometer method that requires procedure of pretreatment and additional 24 hours required for the complete procedure of the test. The various soil samples were collected from seven different locations including Sunway Carnival (Marine Clay), Suling Hills (Residual Clay), Jawi Quarry (Residual Clay), Kelantan River (River Clay), Batu Kawan (Marine Clay), Kaolin Clay and Sungai Petani (Residual Clay). Three soil samples from each site were prepared for the hydrometer method and additional three samples for the new method silt-clay separation. Sample preparation and testing is repeated for all samples from seven site locations. The results of silt clay particle distribution obtained from both experimental works were compared to analyze the compatibility of data. The data analysis shows that there are no significant differences (P > 0.05) between the two methods in all examined soil samples. This indicates strong evidence to support this research that the silt-clay separation new method is comparable to the standard hydrometer method. Regression analysis between the two methods produced a coefficient of determination (R-square) values of 0.9912 respectively. The straight-line equation generated for all data produced the gradient equal to 0.8465, which is close to 1 indicates stronger evidence to supports the accuracy of the new method. In conclusion, the preliminary results of new method silt-clay separation confirmed its reliability to analyze the particle soil distribution in silt-clay fraction with 99.12% data accuracy compared to the standard hydrometer method.

Spatiotemporal characteristics of hydro-meteorological droughts and their connections to large-scale atmospheric circulations in the Kelantan River Basin, Malaysia

Abstract Climate change exacerbates dry seasons in Southeast Asia, leading to water supply shortage. However, the link between hydro-meteorological droughts and large-scale atmospheric circulations, such as the El Nino Southern Oscillation (ENSO), Indian Ocean Dipole (IOD), and Madden–Julian oscillation (MJO), has received very little attention. Therefore, this study aims to analyse the hydro-meteorological droughts that occurred in the Kelantan River Basin (KRB) between 1985 and 2020 using the Standardized Precipitation Index (SPI) and Standardized Streamflow Index (SSI) as well as their connections to ENSO, IOD, and MJO. Sen's slope and Mann–Kendall test were employed to evaluate the trends and magnitude changes of the historical droughts, respectively. In addition, the response rate of SSI to SPI was considered to understand how precipitation affects streamflow. The results show that extremely dry events occurred in 1986, 1987, 1989, 1990, 1992, 1997–1998, 2015–2016, and 2020. Based on the SSI results, more than 70% of extremely dry periods last 6 months or longer. Interestingly, from January to May, when there was low precipitation, SSI had a higher response rate to SPI. The ENSO, as opposed to the IOD and MJO, had a stronger impact on the dry conditions over the KRB.

A multidimensional approach for microplastics monitoring in two major tropical river basins, Malaysia

Microplastics (MPs) with the size of 1 μm–5 mm are pollutants of great concern ubiquitously found in the environment. Existing efforts have found that most of the MPs present in the seas mainly originated from land via riverine inputs. Asian rivers are known to be among the top in microplastic emissions. However, field data are scarce, especially in Malaysia. This study presents the distribution and characteristics of MPs in the surface water of two major river basins of Malaysia, namely Langat River (West Coast/Straits of Malacca) and Kelantan River (East Coast/South China Sea). Water samples were collected at 21–22 locations in Kelantan and Langat rivers, covering the river, estuary and sea. MPs were physically classified based on sizes, shapes, colours and surface morphology (SEM-EDS). The average of 179.6 items/L and 1464.8 items/L of MPs had been quantified from Kelantan and Langat rivers, respectively. Fibre (91.90%) was highly recorded at Kelantan, compared to Langat whereby both fibre (59.21%) and fragment (38.87%) were prevalence. Anthropogenic activities and urbanised areas contribute to high microplastic abundance, especially in the Langat River. Micro-FTIR analysis identified 14 polymers in Kelantan River, whereas 20 polymers were found in Langat River. Polypropylene, polyethylene, polyethylene terephthalate, nylon, phenoxy resins, poly(methyl acrylate), poly(methyl methacrylate), polystyrene, polytetrafluoroethylene, polyurethane and rayon were discovered in both rivers, although only polyethylene was significant (>1 ppm) when further analysed using pyrolysis-GC/MS. Correlation analysis and multiple linear regression were used to explain the relationship between water quality and MP abundance, suggesting only turbidity was positively significant to the microplastic occurrence. This comprehensive study is first to suggest a full-scale monitoring protocol for MPs in Malaysian riverine system and is significant in understanding MPs abundance in correlation to in-situ environmental factors. Consequently, this will allow the right authorities to develop mitigation strategies to address riverine plastic pollution in major river basins in Malaysia and the South East Asia.

Impacts of Solar Radiation Management on Hydro-Climatic Extremes in Southeast Asia

Solar radiation management (SRM), or solar geoengineering, reduces the earth’s temperature by reflecting more sunlight back to space. However, the impacts of SRM remain unclear, making it difficult to project the benefits as well as consequences should this approach be adopted to combat climate change. To provide novel insight into the SRM impact on hydro-climatic extremes in Southeast Asia, this study conducts a simulation experiment for the Kelantan River Basin (KRB) in Malaysia by incorporating three bias-corrected Stratospheric Aerosol Geoengineering Large Ensemble (GLENS) members into the Soil and Water Assessment Tool Plus (SWAT+) model. The study found that SRM practices could generate substantial cooling effects on regional temperatures, leading to a reduction in projected annual precipitation and monthly precipitation during the flooding season (from November to mid-January) under SRM relative to the Representative Concentration Pathway 8.5 (RCP8.5) scenario. In addition, SRM could reduce the number of days with heavy precipitation as well as the intensity of maximum daily precipitation as compared to RCP8.5, during the 2045–2064 and 2065–2084 periods, leading to a reduction in high flows. Nevertheless, under SRM impacts, the driest months from February to May would experience comparable decreases in monthly precipitation and streamflow.

Flood hazard assessment using design rainfall under climate change scenarios in the Kelantan River Basin, Malaysia

Purpose The present study aims to evaluate the effect of climate change on the flood hazard potential in the Kelantan River Basin using current and future scenarios. Design/methodology/approach The intensity-duration-frequency (IDF) was used to estimate the current 50- and 100-year return period 24-h design rainfall, and the climate change factor (CCF) was used to compute the future design rainfall. The CCF was calculated from the rainfall projections of two global climate models, CGCM1 and CCSM3, with different pre-processing steps applied to each. The IDF data were used in the rainfall-runoff-inundation model to simulate current and future flood inundation scenarios. Findings The estimated CCF values demonstrate a contrast, whereby each station had a CCF value greater than one for CGCM1, while some stations had a CCF value of less than one for CCSM3. Therefore, CGCM1 projected an aggravation and CCSM3 a reduction of flood hazard for future scenarios. The study reveals that topography plays an essential role in calculating the CCF. Originality/value To the best of the author’s knowledge, this is the first study to examine flood projections in the Kelantan River Basin. It is, therefore, hoped that these results could benefit local managers and authorities by enabling them to make informed decisions regarding flood risk mitigation in a climate change scenario.

Coupling SWAT and Bi-LSTM for improving daily-scale hydro-climatic simulation and climate change impact assessment in a tropical river basin

Global climate change has led to an increase in both the frequency and magnitude of extreme events around the world, the risk of which is especially imminent in tropical regions. Developing hydrological models with better capabilities to simulate streamflow, especially peak flow, is urgently needed to facilitate water resource planning and management as well as climate change mitigation efforts in the tropics. In view of the need, this paper explores the feasibility of improving streamflow simulation performance in the tropical Kelantan River Basin (KRB) of Peninsular Malaysia through coupling a conceptual process-based hydrological model − Soil and Water Assessment Tool (SWAT) with a deep learning model − Bidirectional Long Short-Term Memory (Bi-LSTM) in two ways. All SWAT parameters were set as their default values in one hybrid model (SWAT-D-LSTM), whereas three most sensitive SWAT parameters were calibrated in the other hybrid model (SWAT-T-LSTM). Comparison of daily streamflow simulation results have shown that SWAT-T-LSTM consistently performs better than SWAT-D-LSTM as well as the stand-alone SWAT and Bi-LSTM model throughout the simulation period. Particularly, SWAT-T-LSTM performs considerably better than the other three models in simulating daily peak flow. Based on the latest projection results of five GCMs from the Sixth Phase of the Coupled Model Intercomparison Project (CMIP6) under three emission scenarios (SSP1-2.6, SSP2-4.5, SSP5-8.5), the best-performed SWAT-T-LSTM was run to assess the potential impacts of climate change on streamflow in the KRB. Ensemble assessment results have concluded that both average and extreme streamflow is much likely to increase considerably in the already wet northeast monsoon season from November to January, which has surely raised the alarm for more frequent flood occurrence in the KRB.

Analysis of River Channel Change Using Remote Sensing Images at Kelantan River Basin

This study presents the utilities of remote sensing technique for analysis of river channel change using remote sensing images at Kelantan River Basin. Understanding river channel change is a key component in developing ecologically friendly and long-term fluvial projects, as well as a way to reduce maintenance costs. The project's study and conclusions will aid in determining how to recognise probable morphological change in river channels. Remote sensing is one of the effective methods for water quality monitoring through image analysis of study area. These tools provide valid means of studying river channel changes. In this study, river channel changes are monitored and quantified by using remote sensing and GIS in Kelantan River. This study focus on four interval years between year 1988 until year 2021 by using Landsat satellite images of 30 m spatial resolution. Landsat Thematic Mapper (TM) 5 images of three different years which are 1988, 1999 and 2010, and Landsat 8 of OLI/TIRS year 2021 were compared. The quantity of accretion and erosion was assessed using parcel-based geoprocessing in a GIS system. The locations are labelled with the year they were created. The area of each year is changing by study period of time for all four interval years 1988, 1999, 2010, and 2021 for research area 1 and 2. The results prove that the river channel in Kelantan is altering, where between 1988 and 2021, the Kelantan River's course has changed significantly. The years 2010 to 2021 are the most severely affected by erosion as a result of the flood in 2014 on the Kelantan River.

Flood River Water Level Forecasting using Ensemble Machine Learning for Early Warning Systems

Flood forecasting is crucial for early warning system and disaster risk reduction. Yet the flood river water levels are difficult and challenging task that it cannot be easily captured with classical time-series approaches. This study proposed a novel intelligence system utilised various machine learning techniques as individual models, including radial basis function neural network (RBF-NN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), and long short-term memory network (LSTM) to establish intelligent committee machine learning flood forecasting (ICML-FF) framework. The combination of these individual models achieved through simple averaging method, and further optimised using weighted averaging by K-nearest neighbour (K-NN) and genetic algorithm (GA). The effectiveness of the proposed model was evaluated using real case study for Malaysia’s Kelantan River. The results show that ANFIS outperforms as individual model, while ICML-FF-based model produced better accuracy and lowest error than any one of the individuals. In general, it is found that the proposed ICML-FF is capable of robust forecasting model for flood early warning systems.

Development of Flood Hazard Index (FHI) of the Kelantan River Catchment Using Geographic Information System (GIS) Based Analytical Hierarchy Process (AHP)

Kelantan has been facing several cases of catastrophic flooding, causing significant damage to this area. Heavy monsoon rainfall is believed to trigger those floods. This study aims to identify and classify the flood occurrence using the Kelantan River catchment’s flood hazard index (FHI) based on the analytical hierarchy process (AHP). This study developed the FHI using the AHP based on spatial analysis in the geographic information system (GIS) environment. Six physical parameters were selected: annual rainfall, slope, river density, land use and land cover (LULC); elevation; and soil permeability. According to the AHP model, the annual rainfall was the first ranked parameter in terms of importance weight score. Moreover, Tanah Merah and Jeli were the high-risk areas for floods. The present study suggests that the GIS-based AHP method can be highly effective for mapping flood hazards and benefit flood management decision-making.

The Effect of Size Distribution on the Geochemistry and Mineralogy of Tropical River Sediments and Its Implications regarding Chemical Weathering and Fractionation of Alkali Elements

Abstract The mineralogical and geochemical compositions of the sediments deposited by rivers have been used extensively to evaluate past chemical weathering and the physical erosion history of drainage basins at different time scales. However, the role of sediment sorting in the mineralogical and geochemical compositions of river sediment needs to be better constrained because it could significantly modify proxies used to evaluate weathering intensity in the past. In this study, major and trace element concentrations and mineralogical compositions were determined on seven different grain-size fractions of riverbed samples taken from the Pahang and Kelantan Rivers in the Malay Peninsula. The main aims are to assess chemical weathering and the fractionation of alkali elements during sediment transportation under tropical climate conditions. Fine sediments (from <2 μm to 4-8 μm) were characterized by higher concentrations of Al2O3, P2O5, V, Sc, and Cs than coarse sediments (from 8-16 μm to 32-63 μm). The presence of heavy minerals, such as zircon and monazite, was found to have critical effects on the concentration of several elements (e.g., Zr and Th), leading to extremely high elemental concentrations in the coarse-sediment fractions. Variations in elemental concentrations with particle sizes are mainly attributed to changes in the mineralogical composition during mineral sorting and weathering. In both rivers, the intensity of chemical weathering increased with decreasing grain sizes. However, the relationship between grain size and chemical weathering trends in the Pahang and Kelantan River basins was different in each case due to differences in plagioclase and K-feldspar concentrations, especially in the coarse-sediment fractions (16-32 μm and 32-63 μm). Kaolinite percentage, illite chemistry index, and illite crystallinity were directly proportional to the chemical index of alteration (CIA), suggesting that these mineralogical parameters are suitable proxies for determining chemical weathering intensity in sediments that have undergone significant changes due to mineral sorting during transportation. The comparison of Rb/K and Cs/K ratios and the CIA suggested that K and Rb mainly derive from primary minerals during the process of chemical weathering, whereas Cs is mainly present in fine weathered particles due to the reabsorption of Cs on clay minerals. Overall, our results highlight the relationship of grain size and mineral assemblages to different states of chemical weathering (and alkali fractionation) in tropical river basin sediments. These relationships need to be considered when using mineralogical and geochemical compositions to reconstruct weathering history in a “source to sink” approach.

Composition of deposited sediment and its temporal variation in a disturbed tropical catchment in the Kelantan river basin, Peninsular Malaysia.

Pristine tropical river systems are coming under increasing pressure from the development of economic resources such as forestry and mining for valuable elements. The Lebir catchment, north eastern Malaysia, is now under development as a result of unregulated tree felling and mining for essential and rare metals. Two sediment cores, one in the upstream reaches and the other from the downstream reaches, were taken from flood prone area of the Lebir River, Malaysia, and analysed for their elemental composition by XRF, specifically Al, Si, Fe, Ca, K, Mg, Mn, V, Cu, Ni, Pb, Cr, Zn, As, Th and U. Activities of fallout radionuclides, 137Cs and 210Pb were also determined to from a geochronological context. The elemental concentrations in the soils were assessed in terms of their enrichment factor and Si, Ca, K, Mg, Mn, V, Cu, Ni and Zn were found not to be enriched, whereas As, Th and U had elevated enrichment factors. The Th and U were particularly enriched in the downstream core indicating inputs from a tributary that drains a catchment with known deposits of Th and possibly U. The results suggest that the growth in economic development is fostering the transport of contaminants by the major rivers which, in turn, is contaminating the riverine floodplains. This points to the need for a more integrated and holistic approach to river basin management to maintain the environmental quality of these fragile aquatic systems.

Prediction of Water Quality Classification of the Kelantan River Basin, Malaysia, Using Machine Learning Techniques

Machine Learning (ML) has been used for a long time and has gained wide attention over the last several years. It can handle a large amount of data and allow non-linear structures by using complex mathematical computations. However, traditional ML models do suffer some problems, such as high bias and overfitting. Therefore, this has resulted in the advancement and improvement of ML techniques, such as the bagging and boosting approach, to address these problems. This study explores a series of ML models to predict the water quality classification (WQC) in the Kelantan River using data from 2005 to 2020. The proposed methodology employed 13 physical and chemical parameters of water quality and 7 ML models that are Decision Tree, Artificial Neural Networks, K-Nearest Neighbors, Naïve Bayes, Support Vector Machine, Random Forest and Gradient Boosting. Based on the analysis, the ensemble model of Gradient Boosting with a learning rate of 0.1 exhibited the best prediction performance compared to the other algorithms. It had the highest accuracy (94.90%), sensitivity (80.00%) and f-measure (86.49%), with the lowest classification error. Total Suspended Solid (TSS) was the most significant variable for the Gradient Boosting (GB) model to predict WQC, followed by Ammoniacal Nitrogen (NH3N), Biochemical Oxygen Demand (BOD) and Chemical Oxygen Demand (COD). Based on the accurate water quality prediction, the results could help to improve the National Environmental Policy regarding water resources by continuously improving water quality.