Reliability of NIRS for Predicting COD, BOD, and TSS Levels in POME, River, and Irrigation Water
Bibliographic record
Abstract
Palm oil mill effluent (POME) contains elevated levels of total suspended solids and organic matter.However, improper disposal of POME, which contains oil, grease, and sludge, can cause ecological damage and pose risks to human health due to its toxic, carcinogenic, and polluting properties.This study aimed to develop a predictive model for pollutant load levels in POME, river water, and irrigation water using near-infrared spectroscopy (NIRS) combined with partial least squares (PLS) analysis.NIR spectral data were collected from 90 samples within the wavelength range of 1000-2500 nm using the FT-NIR Thermo Nicolet Antaris TM II instrument.Pretreatments applied included mean normalization (MN), standard normal variate (SNV), de-trending (DT), and peak normalization (PN).The multivariate analysis was performed using Unscrambler X 10.3 software.Model reliability was assessed using residual predictive deviation (RPD) and range error ratio (RER) as statistical measures for the analysis of chemical oxygen demand (COD), biochemical oxygen demand (BOD), and total suspended solids (TSS).The results showed that the PLS-DT model provided the best results for predicting COD, BOD, and TSS levels in POME, river water, and irrigation water.Predictions of COD, BOD, and TSS levels achieved RPD and RER values of 2.80 and 5.27, 2.89 and 6.05, and 2.05 and 5.39, respectively.Based on the RPD values, the prediction performance for COD and BOD falls into the excellent prediction accuracy category, whereas TSS falls into the coarse quantitative prediction category.RER shows that the prediction model has low to moderate practical utility.These results indicate that NIRS combined with chemometrics can be employed to rapidly and simultaneously predict pollution parameters such as COD, BOD, and TSS.This study improves our knowledge of the pollution load related to the palm oil sector and shows how NIRS and PLS may be used together to monitor the environment effectively and economically.These results encourage initiatives for sustainable environmental management and conservation and advance agriculture and environmental engineering methods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".