Selection and allocation of space for intercropping in rubber plantations to maximize yield and minimum costs for individual farmers involves Multi-Criteria Decision Making (MCDM) and several conditions.  The problem is that the information is scattered in many related agencies, there are separate stores and some data is redundant. In addition, the format of the data varies depending on the purpose of the data. The knowledge of selecting plants to grow in the rubber plantation is the tacit knowledge acquired from the experience of successful farmers in rubber plantations and from agricultural experts. Therefore, this research involves an Integrated Ontology-based knowledge and Multi-Objective Optimization model for intercropping Decision Support Systems (DSS). This article presents the knowledge and integrated data management model for developing the Intercropping in Rubber Plantations Ontology by using the Triangulation in the method to verify the accuracy of the data and results.  Moreover, propose ways to create recommendation rules that are easy to rule update and maintenance.  Using an ontology for DSS helps to recommended plants according to the appropriate environment of the farmer area by rule-based inference to represent logical reasoning.  It could also be applied to another domain that requires Intelligent DSS for MCDM.

The problem of multi-criteria or multi-objective intercropping crop planning makes it vital to consider all related factors under the constraints that will produce the highest revenue and minimum cost. Principles of intercropping elements including soil type, plant area, plant diseases, planting and harvesting time and economics factors (e.g. price, cost) are some of the factors in making decisions. Intercropping is important in the situation such as during inability to harvest main crops, co-cultivation to increase productivity, or even to increase extra revenue. Therefore, the decision-making system requires a wise decision support system, which can advise farmers on economics matters. In this article, we present the decision support system (DSS) model framework for planting rubber with intercropping by a hybrid approach using ontology-based knowledge consuming rule concepts and relationships for intercropping with integrated multi-objectives optimization to recommend the crop to be planted and the suitable proportion of planting areas or planting co-suited to the rubber plantation of farmers. This approach could be applied as a guideline for another field, such as production problems or other resource allocation issues.

No abstract

<span>This research aimed to create suitable forecasting models with long-short term memory (LSTM) from time series data, the price of rubber smoked sheets (RSS3) using 2,631 data from the Rubber Authority of Thailand for the past 10 years. The data was divided into two sets: first series 2,105 data points were used to create the LSTM prediction model; second series 526 data points were used to estimate forecasting performance using the root mean square error (RMSE), the mean absolute percentage error (MAPE), and accuracy rate of the model. The results showed that the most suitable forecasting model for time series data, with a total of 9 LSTM layers comprised of 3 primary LSTMs. Each LSTM layer has the number of neurons 100, 150, and 200 to obtain an optimal neural network of the LSTM technique. The number of epochs and iteration was 30, 40, and 50. Dropout layers between each LSTM layer have a probability of 30%. The results of the test to measure the performance of the time series forecasting data showed that the 9-layer model with the LSTM model architecture of LSTM 3 layers gave the best forecast, with RMSE of 2.4121, MAPE of 0.0413 and 95.88% accuracy rate.</span>