Meti Yulianti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Meti Yulianti has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Iwan Ridwansyah
National Research and Innovation Agency (BRIN)
4 shared publications - Aldiano Rahmadya
National Research and Innovation Agency
2 shared publications - Andi Muhammad Yasser Hakim
Graduate School of Agricultural Science, Hasanuddin University, Makassar, Indonesia
2 shared publications - Fajar Setiawan
National Research and Innovation Agency
2 shared publications - Agus Wuryanta
Research Center for Limnology and Water Resources National Research and Innovation Agency (BRIN) KST-Soekarno BRIN Cibinong Bogor Indonesia
1 shared publication Alifia Imananda
Bogor Agricultural University
1 shared publication
Latest Publications
- 29 October 2026
- Published by Elsevier in Ecohydrology & Hydrobiology
- Vol. 26 (4)
An optimized framework of Landsat for effective surface water quality prediction based on empirical multi-regression structures
- 29 October 2026
- Published by Elsevier in Ecohydrology & Hydrobiology
- Vol. 26 (4)
An optimized framework of Landsat for effective surface water quality prediction based on empirical multi-regression structures
- Open Access
- 30 July 2026
- Published by Elsevier in SSRN Electronic Journal
Representation and Hyperparameter Search in Landslide Susceptibility Modeling: Tree Ensembles and One-Dimensional Convolutional Networks under Nested Spatial Validation
Spatial autocorrelation and arbitrary ordering of heterogeneous conditioning factors can distort algorithm comparisons in landslide susceptibility modeling. This study benchmarks four tree ensembles, a tabular multilayer perceptron, a support-vector classifier, penalized logistic regression, a frequency-ratio reference, and three one-dimensional convolutional architectures using 695 landslide locations, 695 pseudo-absence locations, and 13 conditioning factors in Bogor Regency, Indonesia. Models were evaluated by repeated nested five-fold spatial-block cross-validation using 5 km blocks; tuning was confined to inner training blocks, and discrimination, precision–recall performance, Brier score, expected calibration error, and calibration slope were computed from pooled out-of-fold predictions. Tree ensembles achieved ROC-AUC 0.833–0.839 and PR-AUC 0.848–0.852, whereas the convolutional models achieved ROC-AUC 0.794–0.807. CatBoost exceeded ResNet by 0.032 ROC-AUC (95% CI 0.013–0.051), and random forest exceeded the EfficientNet-inspired 1-D MBConv model by 0.036 (95% CI 0.016–0.062); ResNet and the tabular multilayer perceptron were not distinguishable. Across 30 factor orderings, convolutional ROC-AUC varied by approximately 0.05–0.07. Under an equal budget of 24 unique candidates, six search strategies produced best inner-CV AUCs of 0.723–0.729. TreeSHAP analysis of random forest ranked elevation, geology, terrain ruggedness, NDVI, and soil type as the leading contributors. For this small tabular geospatial dataset and evaluation design, model representation and spatial validation were more consequential than added architectural or metaheuristic complexity.
- 30 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRepresentation and Hyperparameter Search in Landslide Susceptibility Modeling: Tree Ensembles and One-Dimensional Convolutional Networks under Nested Spatial Validation
Spatial autocorrelation and arbitrary ordering of heterogeneous conditioning factors can distort algorithm comparisons in landslide susceptibility modeling. This study benchmarks four tree ensembles, a tabular multilayer perceptron, a support-vector classifier, penalized logistic regression, a frequency-ratio reference, and three one-dimensional convolutional architectures using 695 landslide locations, 695 pseudo-absence locations, and 13 conditioning factors in Bogor Regency, Indonesia. Models were evaluated by repeated nested five-fold spatial-block cross-validation using 5 km blocks; tuning was confined to inner training blocks, and discrimination, precision–recall performance, Brier score, expected calibration error, and calibration slope were computed from pooled out-of-fold predictions. Tree ensembles achieved ROC-AUC 0.833–0.839 and PR-AUC 0.848–0.852, whereas the convolutional models achieved ROC-AUC 0.794–0.807. CatBoost exceeded ResNet by 0.032 ROC-AUC (95% CI 0.013–0.051), and random forest exceeded the EfficientNet-inspired 1-D MBConv model by 0.036 (95% CI 0.016–0.062); ResNet and the tabular multilayer perceptron were not distinguishable. Across 30 factor orderings, convolutional ROC-AUC varied by approximately 0.05–0.07. Under an equal budget of 24 unique candidates, six search strategies produced best inner-CV AUCs of 0.723–0.729. TreeSHAP analysis of random forest ranked elevation, geology, terrain ruggedness, NDVI, and soil type as the leading contributors. For this small tabular geospatial dataset and evaluation design, model representation and spatial validation were more consequential than added architectural or metaheuristic complexity.
- 9 March 2026
- Published by Taylor & Francis in Inland Waters
- Vol. 16 (1)
Stratification and mixing dynamics in tropical polymictic Lake Batur, Indonesia
- 9 March 2026
- Published by Taylor & Francis in Inland Waters
- Vol. 16 (1)
Stratification and mixing dynamics in tropical polymictic Lake Batur, Indonesia
- 8 October 2025
- Published by Taylor & Francis in International Journal of Environmental Studies
- Vol. 83 (1) , 82-100
Analysis of the impact of land use changes on hydrological responses in the Cisadane watershed, Indonesia
- 8 October 2025
- Published by Taylor & Francis in International Journal of Environmental Studies
- Vol. 83 (1) , 82-100
Analysis of the impact of land use changes on hydrological responses in the Cisadane watershed, Indonesia
- 26 November 2024
- Published by Taylor & Francis in Hydrological Sciences Journal
- Vol. 70 (1) , 127-143
Simulating water balance and nutrient losses in a pastoral catchment using the SWAT+ model: added value of isotope data
- 26 November 2024
- Published by Taylor & Francis in Hydrological Sciences Journal
- Vol. 70 (1) , 127-143
Simulating water balance and nutrient losses in a pastoral catchment using the SWAT+ model: added value of isotope data
- Open Access
- 1 January 2024
- Published by Southwest Jiaotong University in Journal of Southwest Jiaotong University
- Vol. 59 (5)
Sensing Total Suspended Solid in a Large Artificial Lake Using Landsat-OLI: A Case Study in Gajah Mungkur Reservoir, Indonesia
Total Suspended Solids (TSS) concentration is one of the key indicators of water quality, reflecting the health of reservoir and watershed ecosystems. Accurate and timely monitoring of TSS is essential for effective management and environmental protection. However, existing models frequently fall short of providing reliable TSS estimates. To address this gap, this study evaluates ten current TSS estimation models and develops a novel model based on Landsat-8/9 OLI data for the Gajah Mungkur Reservoir. The objectives include generating a monthly TSS map and assessing water quality changes over time. We utilized Landsat-8 Level-2 data acquired on March 9, 2023, corresponding with in situ TSS observations collected within the reservoir. The algorithm for TSS estimation was developed through a systematic exploration of various combinations of band ratios derived from bands 2 (Blue), 3 (Green), 4 (Red), and 5 (Near Infrared). Our evaluation revealed that the ten existing models exhibited low accuracy in estimating TSS concentrations in Gajah Mungkur Reservoir, highlighting the need for an improved algorithm. In response, we applied bootstrapping techniques and developed a novel model that utilizes two-band ratios (NIR/Green and Red/Green) of Landsat-8/9 Level-2 data to estimate TSS more accurately. The new model has an R² of 0.78 and a root mean square error (RMSE) of 2.44 mg/L. Hence, we applied the new model to eleven Landsat 8/9 images spanning from February 2022 to March 2023 effectively capturing spatial and temporal variations in TSS concentrations in the Gajah Mungkur Reservoir. The model not only provides accurate TSS estimates but also captures the distribution patterns over time, offering valuable insights for environmental monitoring and management.
- 1 January 2024
- Published by Southwest Jiaotong University in Journal of Southwest Jiaotong University
- Vol. 59 (5)
Open AccessSensing Total Suspended Solid in a Large Artificial Lake Using Landsat-OLI: A Case Study in Gajah Mungkur Reservoir, Indonesia
Total Suspended Solids (TSS) concentration is one of the key indicators of water quality, reflecting the health of reservoir and watershed ecosystems. Accurate and timely monitoring of TSS is essential for effective management and environmental protection. However, existing models frequently fall short of providing reliable TSS estimates. To address this gap, this study evaluates ten current TSS estimation models and develops a novel model based on Landsat-8/9 OLI data for the Gajah Mungkur Reservoir. The objectives include generating a monthly TSS map and assessing water quality changes over time. We utilized Landsat-8 Level-2 data acquired on March 9, 2023, corresponding with in situ TSS observations collected within the reservoir. The algorithm for TSS estimation was developed through a systematic exploration of various combinations of band ratios derived from bands 2 (Blue), 3 (Green), 4 (Red), and 5 (Near Infrared). Our evaluation revealed that the ten existing models exhibited low accuracy in estimating TSS concentrations in Gajah Mungkur Reservoir, highlighting the need for an improved algorithm. In response, we applied bootstrapping techniques and developed a novel model that utilizes two-band ratios (NIR/Green and Red/Green) of Landsat-8/9 Level-2 data to estimate TSS more accurately. The new model has an R² of 0.78 and a root mean square error (RMSE) of 2.44 mg/L. Hence, we applied the new model to eleven Landsat 8/9 images spanning from February 2022 to March 2023 effectively capturing spatial and temporal variations in TSS concentrations in the Gajah Mungkur Reservoir. The model not only provides accurate TSS estimates but also captures the distribution patterns over time, offering valuable insights for environmental monitoring and management.
- Open Access
- 31 December 2023
- Published by National Research and Innovation Agency in Limnotek : Perairan Darat Tropis di Indonesia
Hydrochemical dynamics of stream following rainfall events at agricultural catchments in New Zealand
One of the prerequisites for efficiently managing lake water quality is reliable data regarding the quantity and quality of inflows water, mainly the export of nutrients from the catchment area during rainfall events. We investigated the dynamic characteristics of hydrochemicals concerning rainfall events in agricultural stream waters flowing into eutrophic lakes situated on the North Island’s central plateau of New Zealand. We utilized isotopic composition of water (δ2H-H2O and δ18O-H2O) and nitrate (δ15N-NO3- and δ18O-NO3-) along with high-frequency hydrochemical data for source identification of water and nitrate during a drought period (2020). Our findings indicate that it is essential to initially grasp the fundamental mechanisms associated with rainfall events to formulate effective strategies for minimizing nutrient losses. The methodology outlined in this research integrates stable isotope hydrology with water quality monitoring initiatives, facilitating the understanding and managing the primary governing mechanisms behind diverse contaminant losses from land to adjacent water bodies, explicitly focusing on nitrates. This approach establishes a framework that can assist in devising measures for water quality improvement capable of anticipating the repercussions of substantial rainfall events more effectively.
- 31 December 2023
- Published by National Research and Innovation Agency in Limnotek : Perairan Darat Tropis di Indonesia
Open AccessHydrochemical dynamics of stream following rainfall events at agricultural catchments in New Zealand
One of the prerequisites for efficiently managing lake water quality is reliable data regarding the quantity and quality of inflows water, mainly the export of nutrients from the catchment area during rainfall events. We investigated the dynamic characteristics of hydrochemicals concerning rainfall events in agricultural stream waters flowing into eutrophic lakes situated on the North Island’s central plateau of New Zealand. We utilized isotopic composition of water (δ2H-H2O and δ18O-H2O) and nitrate (δ15N-NO3- and δ18O-NO3-) along with high-frequency hydrochemical data for source identification of water and nitrate during a drought period (2020). Our findings indicate that it is essential to initially grasp the fundamental mechanisms associated with rainfall events to formulate effective strategies for minimizing nutrient losses. The methodology outlined in this research integrates stable isotope hydrology with water quality monitoring initiatives, facilitating the understanding and managing the primary governing mechanisms behind diverse contaminant losses from land to adjacent water bodies, explicitly focusing on nitrates. This approach establishes a framework that can assist in devising measures for water quality improvement capable of anticipating the repercussions of substantial rainfall events more effectively.