No abstract

No abstract

No abstract

Polder system is the key to manage floods in agricultural non-tidal swamp land. Infrastructures to support polder system integrated management include: regional drainage systems, retention ponds, dikes, pumps and/or gates. Pump requirement in an optimally managed polder system is influenced by the polder area, rainfall, soil, and hydrological characteristic. This article presents water balance models application in determining the number and operational duration of pumps to achieve effective and optimal polder function in controlling floods and inundation during the rainy season. This study was conducted in a palm-oil plantation located in lebak swamp area in Pawalutan, Banjang, Hulu Sungai Utara, during September 2016 to September 2017. Pump units and operation durations were calculated based on estimated inundation volumes depending on the water inlet and water balance. Seepage discharge was estimated using Darcy equation. Result of the recovery test measurements showed hydraulic conductivity value of 4.1x10−05 ms−1, while the estimated seepage discharge was 8.6 m3 hr−1 km−1. The pump requirement analysis indicated the need of 55 pump units with 2,500 m3 hr−1 pumping capacity to overcome inundation in the study site with 1,417 ha inundated area. These pumps were distributed into 9 zones, each with 4 to 10 units.

The rice monitoring based on Sentinel-2 (SC-S2) has been developed for over nine months. It has been observed as the first and only system which generate rice growth stages maps in 10 m spatial resolution using machine learning in Indonesia. However, the SC-S2 use Support Vector Machine to separate the rice growth stages, which may have poor performances. The objective of this study is to investigate the performance of other classifiers to increase the performance of SC-S2. We used survey data from the field campaign in 2018 and synchronized with Sentinel-2 bands. The model dataset was trained using 61 machine learning algorithms to create 61 rice growth stages models. The models were applied to the Sentinel-2 image of part of Indramayu area. The accuracy, computational time and visual inspection score were collected, and the final score was calculated. The results are the highest final score is Shrinkage Discriminant Analysis, with overall accuracy 88.1% (p<0.001) and the average accuracy of all classifiers is 76.2% (p<0.05). The implication of this study is to propose some changes in the classification process into the SC-S2 for increasing the overall performance, which will provide better information for agricultural policymakers.