Rain gardens minimize flood peaks, aid groundwater recharging, and enhance biodiversity. The flora in rain gardens serves as a filter media for stormwater treatment. Scutch grass (Cynodon dactylon), Chandani flower (candytuft), marigold, and daisy flower plants were employed in the study for investigating rain garden infiltration rate. According to the findings, bare soil has the lowest average infiltration rate, whereas scutch grass plants infiltration rate is higher. According to the results, the rain garden with the denser scutch grass plant cover infiltrates the water more rapidly than others. This study examines the infiltration capacities of rain gardens by focusing on various plant species, including marigolds, daisy, scutch grass, and candytuft flowers. The experimental data were used to model the infiltration characteristics using a Support Vector Machine (SVM). This model was employed to predict the infiltration rate. The Pearson VII kernel (SVM_PUK) acquired higher values of C.C (0.944), and RMSE (0.6361) for training and testing values of C.C (0.7463), and RMSE (1.1728). The performance criteria suggest that the SVM regression-based Radial basis kernel function has a very good and satisfactory performance.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Assessment of Rain Garden Infiltration Rate Using Support Vector Machine

  • Sandeep Kumar,
  • K. K. Singh

摘要

Rain gardens minimize flood peaks, aid groundwater recharging, and enhance biodiversity. The flora in rain gardens serves as a filter media for stormwater treatment. Scutch grass (Cynodon dactylon), Chandani flower (candytuft), marigold, and daisy flower plants were employed in the study for investigating rain garden infiltration rate. According to the findings, bare soil has the lowest average infiltration rate, whereas scutch grass plants infiltration rate is higher. According to the results, the rain garden with the denser scutch grass plant cover infiltrates the water more rapidly than others. This study examines the infiltration capacities of rain gardens by focusing on various plant species, including marigolds, daisy, scutch grass, and candytuft flowers. The experimental data were used to model the infiltration characteristics using a Support Vector Machine (SVM). This model was employed to predict the infiltration rate. The Pearson VII kernel (SVM_PUK) acquired higher values of C.C (0.944), and RMSE (0.6361) for training and testing values of C.C (0.7463), and RMSE (1.1728). The performance criteria suggest that the SVM regression-based Radial basis kernel function has a very good and satisfactory performance.