Cameron Highland is a popular tourist hub in the mountainous area of Peninsular Malaysia. Most communities in this area suffer frequent incidence of debris flow, especially during monsoon seasons. Despite the loss of lives and properties recorded annually from debris flow, most studies in the region concentrate on landslides and flood susceptibilities. In this study, debris-flow susceptibility prediction was carried out using two data mining techniques; Multivariate Adaptive Regression Splines (MARS) and Support Vector Regression (SVR) models. The existing inventory of debris-flow events (640 points) were selected for training 70% (448) and validation 30% (192). Twelve conditioning factors namely; elevation, plan-curvature, slope angle, total curvature, slope aspect, Stream Transport Index (STI), profile curvature, roughness index, Stream Catchment Area (SCA), Stream Power Index (SPI), Topographic Wetness Index (TWI) and Topographic Position Index (TPI) were selected from Light Detection and Ranging (LiDAR)-derived Digital Elevation Model (DEM) data. Multi-collinearity was checked using Information Factor, Cramer’s V, and Gini Index to identify the relative importance of conditioning factors. The susceptibility models were produced and categorized into five classes; not-susceptible, low, moderate, high and very-high classes. Models performances were evaluated using success and prediction rates where the area under the curve (AUC) showed a higher performance of MARS (93% and 83%) over SVR (76% and 72%). The result of this study will be important in contingency hazards and risks management plans to reduce the loss of lives and properties in the area.

HighlightsClay and clay combined with zeolite was utilized for the production of clay pipes for subsurface micro-irrigation.Various modelling approaches are mathematically complex and require computational and technical skills, hence the need for other simpler approaches.Non-contact imaging and supervised classification (ArcGIS) techniques are utilized for wetting pattern study.The Plexiglas soil column experiment and incorporated techniques provide a visual understanding of soil-water movement interaction.Abstract. The increasing prominence of clay pipes in irrigation water application in drier regions and the importance of soil wetting pattern information requires a better understanding of subsurface irrigation system design and management. This article reported findings on two different porous clay pipes made up of 100% clay, and 25% zeolite as an additive to the 75% clay developed and produced. A new method was proposed to evaluate their performance. A non-contact thermal imaging technique and maximum likelihood supervised classification algorithm on ArcGIS software methods were used for wetting pattern dimensions determination. A Plexiglas soil column filled with homogeneous sandy textured soil profile was used in laboratory experiments. The non-contact thermal imaging technique was used to capture thermal and digital images at different water application times. The images were then classified using a maximum likelihood supervised classification algorithm on the ArcGIS software interface. The results revealed that cumulative water applied increased with an increase in application time. The maximum predicted depth and width for modified pipes were 12.4 and 18 cm, respectively. For the non-modified pipes, the dimension was 11.2 and 17 cm for depth and width, respectively. The maximum recorded wetted area was 46.56% under modified pipes compared with 41.01% for non-modified pipes. The higher uniform area coverage was achieved under modified clay pipes rather than in the clay porous pipes. The study concluded that the proposed imaging technique predicted the soil wetting pattern dimension with acceptable accuracy and provided for a simple and visual approach. Keywords: ArcGIS, Subsurface irrigation, Supervised classification system, Thermal imaging camera, Wetted depth, Wetted width.

Unlike other micro-irrigation facilities like a drip, trickle, and sprinklers that emits water at regularly spaced intervals with predefined discharges, porous rubber pipes (soaker hose) has openings of variable sizes that become unevenly spaced with uneven distribution. The latter makes discharge to be variant along its lateral. Shorter sections are used under laboratory column experiments of soil wetting pattern studies and for this reason, laboratory experiments were conducted to evaluate the extent of emission rates variability on short sections of commercial Irrigation Soaker Hose, 16 mm diameter. Three sections of 10 cm length pipes were randomly selected from 15 no's cuts from different parts of the twenty meters length pipe bundle and used to investigate the extent of variability on emission rates characteristics under six different operating pressures. The result was achieved by collecting and measuring water emitted through the pipe sections at pre-determined pressures. The various discharges, coefficient of variation, and pressure-discharge curves of the section of the pipe then determined from the data. The result shows somewhat similar trends on the increase for water collected with an increase in pressures; however, when statistically compared, the discharges among the pipe sections vary. The values of Coefficient of Variation (CV) are less than 10 % as the values CV range from 0.92 % to 5.82 %, which is within a good category, according to ASAE Standard EP405.1 of 0-10%. The findings indicate that, despite variations among the investigated sections, it can use any part as a representative unit in the soil column experiments with reasonable accuracy.