Validation of CA-Markov for Simulation of Land Use and Cover Change in the Langat Basin, Malaysia

Validity of CA-Markov in land use and cover change simulation was investigated at the Langat Basin, Selangor, Malaysia. CA-Markov validation was performed using validation metrics, allocation disagreement, quantity disagreement, and figure of merit in a three-dimensional space. The figure of merit, quantity error, and allocation error for total landscape simulation using the 1990-1997 calibration data were 5.62%, 3.53%, and 6.13%, respectively. CA-Markov showed a poor performance for land use and cover change simulation due to uncertainties in the source data, the model, and future land use and cover change processes in the study area.

Estimation of red tip disease severity in pineapple using a non-contact sensor approach

Red tip disease on pineapple (Ananas comosus) was first recognized about 20 years ago in a commercial pineapple stand located in Simpang Renggam, Johor, Peninsular Malaysia. Since its discovery, there has been no confirmation on the causal agent of red tip disease. The epidemiology of red tip disease is still not fully understood. However, based on disease symptoms and field transmission mode, red tip disease seems to be strongly associated with viral infection. The aim of this work was to assess the feasibility of using an optical sensor to estimate red tip disease severity. This work was performed in a commercial pineapple plantation located in Simpang Renggam, Johor. Four observation plots bearing pineapple variety SR36 were demarcated based on crop growth stage. Each plot comprised a total of eighty corresponding measurements of percent Disease Severity (% DS) and Normalized Difference Vegetation Index (NDVI). Our data showed a strong correlation between % DS and NDVI. The 7- and 11-month plantings registered a correlation coefficient (r) of -0.83 and -0.88, respectively. The negative correlation infers that NDVI increases when disease severity is low. This is expected since healthy leaves reflect more near-infrared light and less visible light which results in a higher NDVI. The regression of NDVI on % DS for the 7-month planting was explained by: % DS = 181.6 - 185.6*NDVI. Meanwhile, the regression of NDVI on % DS for the 11-month planting was explained by: % DS = 213.2 - 219.8*NDVI. The linear fit between measured % DS and estimated % DS from the 7-month and 11-month plantings was relatively strong. This work has demonstrated that NDVI is a reliable predictor of % DS in pineapple.

Comparison between Multi-Layer Perceptron and Radial Basis Function Networks for Sediment Load Estimation in a Tropical Watershed

Prediction of highly non-linear behavior of suspended sediment flow in rivers has prime importance in environmental studies and watershed management. In this study, the predictive performance of two Artificial Neural Networks (ANNs), namely Radial Basis Function (RBF) and Multi-Layer Perceptron (MLP) were compared. Time series data of daily suspended sediment discharge and water discharge at the Langat River, Malaysia were used for training and testing the networks. Mean Square Error (MSE), Normalized Mean Square Error (NMSE) and correlation coefficient (r) were used for performance evaluation of the models. Using the testing data set, both models produced a similar level of robustness in sediment load simulation. The MLP network model showed a slightly better output than the RBF network model in predicting suspended sediment discharge, especially in the training process. However, both ANNs showed a weak robustness in estimating large magnitudes of sediment load.