PGIA congress 2025

Permanent URI for this collectionhttps://ir.lib.pdn.ac.lk/handle/20.500.14444/7728

Browse

Recent Submissions

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item type: Item ,
    A hybrid machine learning framework for predicting points and continuous soil water retention in tropical soils
    (Postgraduate Institute of Agriculture (PGIA), University of Peradeniya, Sri Lanka, 2025-11-21) Kasthuri Arachchi, K. A. I. L.; Vidana Gamage, D. N.
    Accurate characterization of soil hydraulic properties, including field capacity (FC), permanent wilting point (PWP), and the complete soil water retention curve (SWRC), is fundamental to sustainable water management and hydrological modeling, particularly in heterogeneous tropical environments. However, direct laboratory measurements are resource-intensive and time-consuming and widely used pedo-transfer functions (PTFs) like Rosetta 3 often exhibit limited transferability to tropical soils due to inherent biases in their training data. This study presents a dual-stage computational framework to address these challenges using a sparse, region-specific dataset from Sri Lanka, which was filtered by excluding entries with missing values. First, we develop and validate explainable machine learning (ML) models, demonstrating that ensemble methods such as Random Forest (RF), Extra Trees Regressor (ETR) can accurately predict discrete FC and PWP values (R² > 0.90, RMSE > 3.0). Second, we introduce a novel, physics-informed neural network (NN) that generates continuous and physically plausible SWRCs. This hybrid model integrates a baseline PTF to enforce physical coherence, while a constrained NN trained on local data, refines the output to prevent implausible predictions. The 5-fold cross-validation was employed for unbiased evaluation. All the developed models were significantly outperforming the Rosetta 3 benchmark (R² < 0.37) for predicting FC and PWP. This integrated framework provides a cost-effective, accurate method for characterizing soil hydraulic properties from sparse local data, as a viable alternative to global PTFs, enabling advanced modeling and precision agriculture in data-scarce regions.
  • Thumbnail Image
    Item type: Item ,
    Industrial expansion in Attanagalu Oya river basin: implications of food industry on water resources
    (Postgraduate Institute of Agriculture (PGIA),University of Peradeniya,Sri Lanka, 2025-11-21) Weerasooriya, W. M. N. L.; Dayawansa, N. D. K.; Mowjood, M. I. M.; De Silva, R. P.
    Attanagalu Oya river basin in the western province of Sri Lanka has witnessed a rapid industrial growth over the last twenty years due to its accessibility to transportation, infrastructure and wealth of water resources. This study assesses how industrial expansion has exerted pressure on freshwater resources, focusing on the food and beverage industry. Methodology involves the analysis of rainfall from five gauging stations, monthly river discharge data from Dunmale (20052023), and water quality measurements. Water quality was monitored at monthly intervals for six months (January to June, 2025) at sampling 10 points for Dissolved Oxygen (DO), Chemical Oxygen Demand (COD), Total Dissolve Solids (TDS), Practical Salinity Units (PSU), and pH. Monthly discharge analysis indicates two distinct periods: high flow (May and October – November) and low flow (February and August). Currently, a total of 47 factories are located within the study area. Downstream water quality (samplings point 6-10) shows severe pollution, with persistently low DO and statistically significant monthly variation (p<0.05). During the low flow in February, DO decreased in midstream to downstream areas, accompanied by elevated COD (up to 217 to 189mg/ L) and elevated Salinity and TDS (741 mg/L) exceeding SLS limit of 500mg/L. In contrast, high flow in May improved water quality through dilution, reducing COD to 6 – 98 mg/L, TDS to 49 – 68 mg/L and PSU to 0.04- 0.06. Overall the results confirm that river discharge dynamics directly influence pollutant dispersion, and industrial expansion has led to measurable freshwater degradation. Evident-based, sector-specific regulations are required for water abstraction and effluent discharge.