YGYasas Gamagedara

Yasas Gamagedara

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yasas Gamagedara has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Unlock Soil Spectra: Moisture Impact and Correction of Visible, Near and Mid Infrared Spectra From Airdry to Field‐Wet

    by Chamika A. Silva, Nuwan K. Wijewardane, Yasas Gamagedara, Michael S. Cox, Xin Zhang

    Moisture is the most significant limiting factor for the field application of soil spectroscopy. Understanding this impact on spectra qualitatively and quantitatively will help identify ways to eliminate it, enabling cost‐effective use of the technology for field‐level applications. Considering this, two objectives were identified and tested: (1) to evaluate how the moisture systematically impacts visible/near‐infrared (VisNIR) and mid‐infrared (MIR) spectra at different moisture levels, (2) to compare three different calibration transfer techniques to enable the transferring of field level scans to airdry condition. Spectra were collected by three spectrometers in the VisNIR and MIR regions. From a total of 473 soil samples, 272 samples were used to develop dry ground models with partial least square regression to predict different soil properties. The remaining 201 samples were rewetted to nine different moisture levels. One hundred samples were used for calibration transfer and the rest as the test set. The results showed that MIR spectra were significantly affected by moisture. Spiking with extra weights outperformed other techniques and the improvements were consistent across different moisture levels. With spiking, Calcium showed the highest improvement with an increase of R 2 from 0.05 to > 0.84 and the ratio of performance to interquartile range from 0.14 to > 1.60. The study showed that the optimum number of samples for the calibration transfer depends on several factors including spectrometer, moisture correction method and the moisture content of the testing set. The study concluded that spiking can be considered a reliable and robust approach for moisture correction in in situ soil spectroscopy.

  • Open Access

    Explainable machine learning for predicting POXC and organic carbon from mid-infrared spectra under varying soil scanning conditions

    by Yasas Gamagedara, Nuwan K. Wijewardane, Shankar Ganapathi Shanmugam, Nisarga Kodadinne Narayana, Praveen S.A. Amarasinghe Arachchige

  • Open Access

    Spectroscopy-based models outperform pedotransfer functions for estimating soil hydraulic properties

    by Yasas Gamagedara, Gary Feng, Travis Waiser, Michael Williams, Mary Love Tagert, Vitor S. Martins, Nuwan K. Wijewardane


  • Open Access

    Comparative Analysis of Raw and Preprocessed Vis–NIR and MIR Spectra for Soil Property Estimation

    by Yasas Gamagedara, Nuwan K. Wijewardane

    Demand for rapid and cost-effective soil analysis has increased the use of spectroscopy, particularly in the visible–near-infrared (Vis–NIR) and mid-infrared (MIR) regions. Using 8304 soil samples from the United States Department of Agriculture spectral library, this study evaluated the effects of raw and preprocessed spectra on the prediction accuracy of eleven key soil properties across Vis–NIR and MIR regions using multiple machine learning algorithms. Spectral preprocessing, combining baseline correction and standard normal variate transformation, consistently improved prediction accuracy compared to the raw spectra. Overall, MIR-based models consistently outperformed Vis–NIR across all soil properties, with the largest performance gains observed for potassium, bulk density, and nitrate nitrogen. Among the machine learning approaches evaluated, artificial neural networks and categorical boosting algorithms provided the strongest and most consistent predictive performance across both spectral regions. These findings demonstrate that combining appropriate spectral preprocessing, spectral region selection, and advanced machine learning algorithms can substantially improve soil property prediction using spectroscopy.


  • Application of calibration transfer techniques between different mid‐infrared spectrometers/modules to improve accuracy in estimating soil properties

    by Yasas Gamagedara, Gary Feng, Travis Waiser, Mary Love Tagert, Vitor S. Martins, Nuwan K. Wijewardane

    Diffuse reflectance spectroscopy offers a rapid and cost‐effective alternative to traditional soil property measurement. Advances in spectrometer technologies have enhanced portability and affordability, expanding their use for soil property estimation. However, developing training datasets for new spectrometers is expensive and time‐consuming. Leveraging existing spectral datasets is crucial, yet variations between different spectrometers reduce prediction accuracy. To address this issue, we conducted model training and testing using Mississippi and Texas datasets from the USDA National Soil Survey Center–Kellogg Soil Survey Laboratory mid‐infrared (MIR) spectral library ( n = 2564) and regional dataset ( n = 1521) across four Fourier‐transform MIR spectrometers/modules. We assessed calibration transfer techniques using preprocessing (individual/combinations) and spectral/model transfer for predicting soil properties. Among preprocessing techniques, combination of first derivative with Savitzky–Golay, baseline correction (BC), standard normal variate (SNV), and combination of BC, SNV outperformed others, though no single approach was optimal for all properties. Spectral/model transfer techniques such as external parameter orthogonalization and spiking effectively harmonized predictions, while slope‐bias correction, direct standardization, and piecewise direct standardization showed limited success. A combined approach of BC and SNV spiking significantly improved model performance across spectrometers/modules and soil properties. On average across all the soil properties, the mean R 2 improvement compared to models trained without calibration transfer was 0.354 when using the spectral library for training and regional dataset for testing, and 0.401 when using regional dataset for both training and testing. This study demonstrated that existing spectral datasets can be effectively used for new spectrometers with calibration transfer, allowing real‐time and field‐scale soil property measurement.


  • Open Access

    Can we use a mid-infrared fine-ground soil spectral library to predict non-fine-ground spectra?

    by Yasas Gamagedara, Nuwan K. Wijewardane, Gary Feng, Cathy Seybold, Michael Williams, Mary Love Tagert, Vitor S. Martins