Landslide incidents frequently occur in the upper northern region of Thailand due to its topography, which is mostly mountainous with high slopes. In the past, when landslides happened in this area, they affected traffic accessibility for rescue and evacuation. For this reason, if the risk of landslides could be evaluated, it would help in the planning of preventive measures to mitigate the damage. This study was carried out to create and develop a risk estimation model using the artificial neural network (ANN) technique for landslides at the edge of the roadside, by collecting field data on past landslides in the study areas in Chiang Rai and Chiang Mai Provinces. A total of 9602 data points were collected. The variables for forecasting were: (1) land cover, (2) physiographic features, (3) slope angle, and (4) five-day cumulative rainfall. Two hidden layers were used to create the model. The number of nodes in the first and second hidden layers were five and one, respectively, which were derived from a total of 25 trials, and the highest accuracy achieved was 96.74%. When applying the model, a graph demonstrating the relationship between the landslide risk, rainfall, and the slopes of the road areas was obtained. The results show that high slopes result in more landslides than low slopes, and that rainfall is a major trigger for landslides on roads. The outcomes of the study could be used to create risk maps and provide information for developing warnings for high-slope mountain roads in the upper northern region of Thailand.

Stormwater runoff is an issue that is increasingly affecting urban areas because areas that previously were permeable have been developed, and are now impermeable, comprising hard surface areas, whether concrete floors, roads, or buildings. As the size of the problem area increases, the amount of stormwater runoff that needs to be cleared from urban areas increases, and it takes longer for the stormwater to be cleared. The existing basic public drainage systems can no longer sufficiently support the increasing stormwater runoff, directly affecting commuting and lifestyle. These problems have led to the design concept of bioretention, which can be used to increase the efficiency of water infiltration of existing soil areas since a higher water infiltration rate can help relieve the burden on the basic public drainage system and alleviate the abovementioned problems. Bioretention design consists of three layers: the drainage layer at the bottom, the transition layer, and the filter media layer at the top. The critical objective is to design the filter media layer (the top layer) to have a greater infiltration rate than the original soil. This research, therefore, comprises an experiment in which sand is mixed with the original soil to achieve these increased infiltration rates. Three different soil-to-sand ratios were field tested within the area of the Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand with double-ring infiltrometer technique to test the infiltration rate, 1:1, 1:2, and 1:4. This research also applied Horton's Theory of Perforation Prediction Equations; the experiments demonstrated that adding sand can increase the water infiltration rate. The infiltration rates for soil-to-sand ratios of 1:1, 1:2, and 1:3 are 16.09, 21.53, and 28.90 mm/hr., consecutively. In addition, understanding the relationship between infiltration rate and sand ratio makes it possible to determine the permeation rate as required. Furthermore, knowing the sand ratio is useful for future planning to achieve the appropriate design.