Klastering Tingkat Pemakaian Pompa Air Tanah Menggunakan Model Fuzzy
Muhammad Aqil, I.U. Firmansyah & Moses Macalino, Balai Penelitian Tanaman Serealia - Maros.
The paradigm of fuzzy analysis as a fundamental tool for data analysis has been found useful in fuzzy modeling. In the present research, an applicability of fuzzy logic approach in clustering of groundwater pump utilization is examined. The task of the clustering system was used for classification of the groundwater pump categorical data based on their attribute similarities. The methodology is illustrated through the case study of groundwater pump system located in Madiun Regency, East Java-Indonesia. The results indicate that fuzzy c-means clustering applied in the operation characteristics of groundwater pumps have reached encouraging results for the groundwater system under study. The final result comprises of four groups; one group with low utilization and one group with high utilization of groundwater pump for irrigation, whereas the remainder belonged to a less moderate utilization group and a moderate utilization group. Region I was dominated by shallow groundwater pumps with low discharge. Region II and III were dominated by medium to deep groundwater pumps. Another feature of the pumps operated in these regions was their usage below design potential. Meanwhile, pumps operating in Region IV was dominated by deep well pump and exploited more intensively than those in the other groups. This finding is useful in determining the potential or possible locations of the future groundwater development projects.
Download pdf file (297 kb)
Rizatus Shofiyati & Dwi Kuncoro, Balai Besar Pewnelitian dan Pengembangan Sumberdaya Lahan Pertanian - Bogor.
Remote sensing provides an efficient technology with capabilities of capturing, generating and analyzing the spatial data. Integrating two analysis of Normalized Difference Vegetation Index (NDVI) and Wetness of Tasseled cap transformation (TCT) or Brightness Temperature (BT) have been applied for identifying and assessing agricultural drought. Spectral signature derived from Landsat satellite data is also very effective for recognizing condition of vegetation that can be implemented for drought identification. The research activities have been conducted in agricultural land located in Citarum Watershed, Northern Coast of West Java Province and Brantas Watershed, East Java Province, which are known as a central areas of rice production in which some locations are suffered due to drought condition. The results of the analysis showed that remote sensing data could be used to identify, assess, and monitor drought on agricultural land. This information of drought distribution which is derived from satellite data analysis could give the alternatives to anticipate the efforts in accordance with its condition.
Download pdf file (276 kb)
Wayan R. Susila, Lembaga Riset Perkebunan Indonesia - Bogor.
One of the main problems causing a setback of Indonesian sugar industry is inefficiency in farm and plant levels because of lack of integrated production system. In response to this problem, this study aims to build a model of integrated production systems between farm and sugar plant activities through an integrated planting and harvesting schedule. The approach used is a compromise approach using a multi party multi objective (MPMO) models. The results of this study showed that productivity in farm and sugar plant can be improved by developing an integrated production system through an integrated planting and harvesting schedule. With supervisions and model modification, the MPMO model can be applied, especially for sugar plantation in Java.Download pdf file (286 kb)
M. Yasin HG, Roy Efendy & Made J. Mejaya, Balai Penelitian Tanaman Serealia - Maros.
ASI (Anthesis Silking Interval) is the difference between silking and anthesis period of maize, the small value of ASI on population or inbred lines was being increasing of yield. The relation between ASI (x) and yield (y) was an exponential model with negative coefficient of β. The experiment was conducted on family S1 of population Pool-2(S1)C8 under drought condition in Bulukumba South Sulawesi, and population AMATL(S1)C6 under deficient nutrient on RYP (Red Yellow Podzolic) in Natar Bandar Lampung. Alfa lattice design with two replications. Was used in this study.
The result shown that the model exponential under (1) drought condition was y = 31.912e-0.295x, R2= 75.22% and under RYP (2) was y = 129.412e-0.451x; R2=79.14%. The test hypothesis of homogeneity coefficient of β (slope) on two models after anti-log shown that two coefficient of β were not significant under drought and deficient nutrient. The statistical test was used t-student model with d.f. (n1+n2-4) on 95 % level of significant, and could be predicted if ASI of Pool-2(S1)C8 and AMATL(S1)C2 were more than six days, then there would be no yield.
Download pdf file (237 kb)
Wieta B. Komalasari, Pusat Data dan Informasi Pertanian - Jakarta.
Regression trees are used to predict membership of cases or objects in the classes of a categorical dependent variable from their measurements on one or more predictor variables. Regression tree analysis is one of the main techniques used in so-called data mining. The goal of regression trees is to predict or explain responses on a categorical dependent variable. The flexibility of regression trees make them a very attractive analysis option, but this is not to say that their use is recommended to the exclusion of more traditional methods. Indeed, when the typically more stringent theoretical and distributional assumptions of more traditional methods are met, the traditional methods may be preferable. But as an exploratory technique, or as a technique of last resort when traditional methods fail, regression trees are, in the opinion of many researchers, unsurpassed. This research used data from survey on farmer income conducted by BPS-Statistics Indonesia (for Jawa TimurProvince) in 2004, and regression method based on tree structure with CART algorithm to build a model. The results show that farmer’s income is interconnected with expenditure of farming activities and land ownership. Despitefully, there are other non-technical factors that also can influence the income. This factors among others the social condition of pertinent agriculture household, for example, education level, age and also other external factors such as soft loan from government and agriculture counseling. These matters indicate that the earnings from farming activities is represented by the function of those factors.
Download pdf file (418 kb)