2026-10-11T15:04:29Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33978254 2026-09-24T01:13:46Z category_146 category_16 category_873 category_45 category_734 category_133 portal_63 item_type_3 month_year_09_2026

Small Sample Machine Learning for Predicting Composition Changes in Chemically Pretreated Kapok Fiber Yitong Niu (22658927) Ireland LaBass (25100258) Ying Ying Tye (22658930) Tristan Smith (17332111) Sicheng Wang (5812403) Yunxiang Li (2575021) Ting Han (170267) Cheu Peng Leh (22658933) Space Science Physiology Chemical Sciences not elsewhere classified Sociology Biological Sciences not elsewhere classified Plant Biology useful exploratory tool three process descriptors strongest performance (< importance analysis indicated findings position limited evaluated using leave associated pretreatment environment 33 pretreatment runs predicting composition changes data machine learning based multitarget modeling related composition changes 2 </ sup lignin contents used 2 </ sub composition targets r </ related variation data set >< sup waxy surface solid yield shared window sample size residence time renewable feedstock reduce dependence predictable component output modeling naoh across kapok fibers kapok fiber dominant descriptor dependent predictability also highlighting Kapok is a lightweight hollow tropical fiber with potential as a renewable feedstock, but its waxy surface and lignin-containing matrix complicate aqueous processing. This study evaluated whether limited-data machine learning could predict kapok fiber composition after aqueous chemical pretreatment using only three process descriptors. Kapok fibers were pretreated using dilute H₂SO₄, hydrothermal water, and NaOH across a shared window of residence time, temperature and pH-associated pretreatment environment. A data set of 33 pretreatment runs was constructed, with cellulose, hemicellulose and lignin contents used as composition targets after correction with solid yield. Single-output and wrapper-based multitarget regression models were screened and then evaluated using leave-one-out cross-validation to reduce dependence on a single train–test split. The LOOCV results showed target-dependent predictability. In single-output modeling, cellulose was the most predictable component, with GBDT giving the strongest performance (<i>R</i>² = 0.782; RMSE = 4.185 percentage points), whereas hemicellulose and lignin showed weaker prediction. In wrapper-based multitarget modeling, GBDT improved simultaneous prediction of cellulose, hemicellulose and lignin, giving <i>R</i>² values of 0.909, 0.653, and 0.672, respectively. Feature-importance analysis indicated that temperature was the dominant descriptor for polysaccharide-related composition changes, whereas the pH-associated pretreatment environment contributed more strongly to lignin-related variation. These findings position limited-data machine learning as a useful exploratory tool for modeling pretreatment–composition relationships in kapok fiber, while also highlighting the need for cautious validation when sample size is small. 2026-09-23T00:00:00Z Dataset Dataset 10.1021/acsomega.6c04765.s001 https://figshare.com/articles/dataset/Small_Sample_Machine_Learning_for_Predicting_Composition_Changes_in_Chemically_Pretreated_Kapok_Fiber/33978254 CC BY-NC 4.0