Hasil Pencarian  ::  Simpan CSV :: Kembali

"Rice fields located in Citarum Hilir watershed of Karawang district are more and more affected by growth of residential and industrial areas. This resulted in the need to have supporting rice fields elsewhere including in the upstream region. ln Citarum Hulu watershed, 19,5% fiom the existing rice fields is non-irrigated with 32,l9% of population work in the agriculture sector. But productivity of' non-irrigated rice fields of Citanim Hulu watershed is still low, which is below 25 kwintal/ha. One of the efforts to increase its productivity is to look at the local climate model. The low productivity may also be caused by factors such as slope and altitude, which are used as variables in Wilayah Tanah Usaha (WTU). Sandy (1985) wrote that growth and death of any plant in Indonesia depend on water. Awarding to Chang (1968) every process in a plant is affected by water. Furthermore, FAO believed that the growth requirement of a rice plant is also depended on water availability. Mohr, Schimdt-Ferguson, and Oldeman made climate classifications based on rainfall in relation with plant needs of irrigation. Spatial climate model and planting time/season are important factors in management of non-irrigated rice fields in Citarum Hulu watershed. These rice fields are nou-unifonnly found in the center down to the south. Rice production varies from 22 to 4l kw/ha where the majority produces 30-40 kw/ha. Productivity model for the northem part is varied, and to the south is more stable with productivity of 30-40 kw/ha. The annual average rainfall in Citarum Hulu watershed is 1770-3458 mm/yr where the majority of the region has in the range of 2000-3000 mm/yr. Maximum monthly rainfall is 558 mm and a minimum of 6 mm on average. Rainfall is high in the months of November to April and dry period is fiom June to August. Mol-rr?s climate classification is around class III - Vb where the majority is in class III-IV. Schmidt-Ferguson?s climate classification for this area is type C to type A, where the majority is in the wet type (A). 0Ideman?s climate classification varies from D3 to Bl where the majority ofthe region is in climate group C-B (humid-wet). ln general, climate model for Citarum Hulu watershed is as follows: in the center (around the city of Bandung) is almost always drier than its surrounding areas, specifically in the northem and southem parts that are mountainous. The distribution of non-irrigated rice fields has a strong correlation with the annual rainfall model of Schimdt-Ferguson and Oldeman, because as an area has more precipitation there tend to be non-irrigated rice fields. But it is not true with Mohr climate. A strong correlation in productivity of non-irrigated rice fields with rainfall model, Mohr, Schmidt-Ferguson, and Oldeman climate models mean that as a region receives more precipitation then 'there is a tendency of higher rice productivity. But there is also a tendency that if an area is extremely wet, the productivity will decrease. Planting season in the Citarum Hulu watershed is from October and May with 4 planting time models: October/February, October/March, November/March, and December/April. In the November/March, planting time is dominant in almost all of the watershed area. Part of the non-irrigated rice fields in Citarum Hulu watershed are still according to the WTU conception, that is 65,87%, which the majority is in the center. As for the rest of this region, they should be converted into protected forest areas (especially in the south) and hard plant agriculture (in the cast). Keywords: DAS Citarum Hulu, non-irrigated rice fields, rainfall, climate model, Mohr, Schmidt-Ferguson, Oldeman, WTU conception, planting time."

"Klasifikasi curah hujan sangat membantu masyarakat dan instansi terkait dalam mengambil kebijakan seperti pengelolaan sumber daya air, transportasi, pertanian dan pencegahan bencana. Model yang sudah pernah digunakan dalam melakukan klasifikasi curah hujan yaitu XGBoost, telah terbukti mampu melakukan klasifikasi dengan efektif, namun masih memerlukan tuning pada hyperparameter-nya untuk meningkatkan performa model. Penelitian ini bertujuan untuk merancang metode klasifikasi curah hujan dengan model XGBoost dan menemukan nilai learning rate terbaik untuk klasifikasi curah hujan. Parameter max depth, dan n estimator ditetapkan berdasarkan penelitian yang sudah pernah dilakukan. Model ini dibangun berdasarkan data historis curah hujan selama 3 bulan setiap jam, yang telah dikumpulkan oleh peralatan Automated Weather Observed System (AWOS) di Stasiun Meteorologi Kota Pontianak. Pencarian hyperparameter menggunakan metode coarse to fine, yaitu pencarian kasar ke pencarian halus. Pencarian kasar menggunakan RandomizedSearchCV, sedangkan pencarian halus dengan GridSearchCV. Model dievaluasi dengan metrik Accuracy, precision, recall, dan F1-score. Evaluasi menunjukkan bahwa model memilki metrik evaluasi yang baik dengan persentase diatas 80% untuk setiap kasus pembagian data. Nilai learning rate terbaik dengan akurasi tertinggi yang didapatkan pada model dengan 2040 data set adalah pada kasus klasifikasi biner, yaitu sebesar 0.043 dengan akurasi pada data latih 90.19%.

---

The classification of rainfall is very helpful for the community and related agencies in making policies such as managing water resources, transportation, agriculture, and disaster prevention. The model that has been used to classify rainfall, namely XGBoost, has proven to be able to classify effectively but still requires tuning its hyperparameters to improve model performance. This study aims to design a rainfall classification method using the XGBoost model and find the best learning rate for rainfall classification. The max depth and n estimator parameters are determined based on research that has been done. This model was built based on historical rainfall data for 3 months every hour, which has been collected by the Automated Weather Observed System (AWOS) equipment at the Pontianak City Meteorological Station. The hyperparameter search uses the coarse-to-fine method, which is a coarse-to-fine search. The coarse search uses RandomizedSearchCV, while the fine search uses GridSearchCV. The model is evaluated with Accuracy, precision, recall, and F1-score metrics. The evaluation shows that the model has good evaluation metrics with percentages above 80% for each case of data sharing. The best learning rate value with the highest accuracy obtained in the model with the 2040 dataset is in the binary classification case, which is equal to 0.043 with an accuracy of 90.19% of the training data."

"The book shows validation of precipitation modeling against observations and derives a set of diagnostic precipitation equations. The book provides detailed discussions of the applications of precipitation equations to the examination of effects of sea surface temperature, vertical wind shear, radiation, and ice clouds on torrential rainfall processes in the tropics and mid-latitudes, and to the studies of sensitivity of precipitation modeling to uncertainty of the initial conditions and to the estimate of precipitation efficiency. "

"This book combines theoretical concepts with experimental results on thermal microwave radiation to increase the understanding of the complex nature of terrestrial media. With the emphasis on radiative transfer models, this new book covers the urgent needs for the transition from the experimental phase of microwave remote sensing to operational applications. This book covers all terrestrial aspects from clear to cloudy atmosphere, precipitation, ocean and land surfaces, vegetation, snow and ice.A chapter on new results of microwave dielectric properties of natural media, covering wavelengths from the decimetre to the submillimetre range, will be a source for further radiative transfer developments, which extends the applicability to radar and other electromagnetic tools, which include extraterrestrial objects, for example planets and comets."