Rice Mapping in Training Sample Shortage Regions Using a Deep Semantic Segmentation Model Trained on Pseudo-Labels

A deep semantic segmentation model-based method can achieve state-of-the-art accuracy and high computational efficiency in large-scale crop mapping. However, the model cannot be widely used in actual large-scale crop mapping applications, mainly because the annotation of ground truth data for deep semantic segmentation model training is time-consuming. At the operational level, it is extremely difficult to obtain a large amount of ground reference data by photointerpretation for the model training. Consequently, in order to solve this problem, this study introduces a workflow that aims to extract rice distribution information in training sample shortage regions, using a deep semantic segmentation model (i.e., U-Net) trained on pseudo-labels. Based on the time series Sentinel-1 images, Cropland Data Layer (CDL) and U-Net model, the optimal multi-temporal datasets for rice mapping were summarized, using the global search method. Then, based on the optimal multi-temporal datasets, the proposed workflow (a combination of K-Means and random forest) was directly used to extract the rice-distribution information of Jiangsu (i.e., the K–RF pseudo-labels). For comparison, the optimal well-trained U-Net model acquired from Arkansas (i.e., the transfer model) was also transferred to Jiangsu to extract local rice-distribution information (i.e., the TF pseudo-labels). Finally, the pseudo-labels with high confidences generated from the two methods were further used to retrain the U-Net models, which were suitable for rice mapping in Jiangsu. For different rice planting pattern regions of Jiangsu, the final results showed that, compared with the U-Net model trained on the TF pseudo-labels, the rice area extraction errors of pseudo-labels could be further reduced by using the U-Net model trained on the K–RF pseudo-labels. In addition, compared with the existing rule-based rice mapping methods, he U-Net model trained on the K–RF pseudo-labels could robustly extract the spatial distribution information of rice. Generally, this study could provide new options for applying a deep semantic segmentation model to training sample shortage regions.

Optimizing Rice Distribution Model Using Linear Programming at West Java Bulog

Good distribution network management is a very important competitive advantage for a company. West Java Bulog is the representative of the government in distributing and distributing rice, which is a staple food commodity for the Indonesian people in general, of course, must pay attention to the optimal distribution pattern. In carrying out its operational processes, West Java Bulog will be assisted by 7 regional subdivisions spread throughout the West Java region who will handle rice in their respective working areas. This study aims to determine the planning path and the optimum amount of rice distribution from the West Java Bulog to districts and cities that can minimize distribution costs so that the costs incurred will reach the lowest point using the Linear Programming method. The analysis of this research was assisted by LINDO Software version 7.0 for Windows 10.0. From the results of this study, the optimization of rice distribution at the West Java Bulog, with the optimum total distribution cost of USD 124,272.

Optimization of Rice Distribution Using a Linear Programming Model at Perum Bulog, West Java Regional Division, Indonesia

Good distribution network management is a very important competitive advantage for a company. The distribution that is not right with the wrong time will also have a big impact on all aspects, especially company profits. The exact number and timing are crucial points in the distribution. The distribution and transportation system must be designed optimally so that the minimum cost is obtained. Perum Bulog, West Java Regional Division, is the government's representative in distributing rice evenly and distributing rice, which is a staple food commodity for Indonesian people in general. Of course, it must pay attention to optimal distribution patterns. In carrying out the operational process, the West Java Regional Division of Perum Bulog will be assisted by 7 Regional Sub-Divisions scattered throughout the West Java region who will handle rice in their respective working areas. This study aims to determine the planning path and the optimum amount of rice distribution from the West Java Regional Division to districts and cities that can minimize distribution costs so that the costs incurred will reach their lowest point using the Linear Programming method. The analysis of this research was assisted by the LINDO software version 7.0 for Windows 10.0. From the results of this research, the optimization of rice distribution at Perum Bulog Divre West Java, with the optimum total distribution cost is IDR 6,374,025 360.

Rice Mapping Using a BiLSTM-Attention Model from Multitemporal Sentinel-1 Data

Timely and accurate rice distribution information is needed to ensure the sustainable development of food production and food security. With its unique advantages, synthetic aperture radar (SAR) can monitor the rice distribution in tropical and subtropical areas under any type of weather condition. This study proposes an accurate rice extraction and mapping framework that can solve the issues of low sample production efficiency and fragmented rice plots when prior information on rice distribution is insufficient. The experiment was carried out using multitemporal Sentinel-1A Data in Zhanjiang, China. First, the temporal characteristic map was used for the visualization of rice distribution to improve the efficiency of rice sample production. Second, rice classification was carried out based on the BiLSTM-Attention model, which focuses on learning the key information of rice and non-rice in the backscattering coefficient curve and gives different types of attention to rice and non-rice features. Finally, the rice classification results were optimized based on the high-precision global land cover classification map. The experimental results showed that the classification accuracy of the proposed framework on the test dataset was 0.9351, the kappa coefficient was 0.8703, and the extracted plots maintained good integrity. Compared with the statistical data, the consistency reached 94.6%. Therefore, the framework proposed in this study can be used to extract rice distribution information accurately and efficiently.

Perhitungan Reduksi Emisi Gas Buang Melalui Penentuan Rute Distribusi Beras di Kota Bandung

ABSTRACT Total transport energy use and carbon emissions in 2030 are estimated to be about 80% higher than at present. West Java's transportation sector emissions are projected to occupy the third position in the third-largest contributor to GRK emissions, amounting to 21.9 million tons of CO2. The West Java Provincial Government aims to reduce 3.18 million tons of CO2 eq for the energy sector and 1.1 million tons of CO2 eq for the transportation sector. Of course, this is a challenge for the government because the volume of truck logistic systems continues to increase, especially in Bandung. The purpose of this study is to determine the value of truck exhaust emissions produced and to know what strategies should be taken to reduce exhaust emissions based on the selection of distribution routes for rice distribution in Bandung City. This study uses an ILP model with a Matlab solver that compares the total mileage, the number of vehicles, and total transportation costs in two distribution systems, namely direct delivery and shared delivery. In this study, the scenario of the transport capacity was changed according to the use of the truck type fuso tub, changing the type of truck that has a larger capacity, and calculating the value of exhaust emissions for trucks in both new scenarios and two distribution systems. The results showed, to reduce exhaust emissions by adjusting the number of vehicles and the minimum total mileage through increased transport capacity and sharing delivery systems, this strategy can reduce exhaust emissions by 21.92% for each composition. Keywords: transportation, rice distribution, sharing delivery, emission reduction, exhaust emission ABSTRAK Total penggunaan energi transportasi dan emisi karbon pada tahun 2030 diperkirakan menjadi sekitar 80% lebih tinggi daripada kondisi saat ini. Pada emisi sektor transportasi Jawa Barat diproyeksikan pada tahun 2020 menempati posisi ketiga terbesar penyumbang emisi GRK sebesar 21,9 juta ton CO2. Pemerintah Provinsi Jawa Barat memiliki target menurunkan 3,18 juta ton CO2-eq untuk sektor energi dan 1,1 juta ton CO2-eq untuk sektor transportasi. Tentu hal ini menjadi tantangan pemerintah karena faktanya pada sistem logistik volume kendaraan truk terus meningkat khususnya di Kota Bandung. Tujuan dari penelitian ini adalah untuk mengetahui nilai emisi gas buang kendaraan truk yang dihasilkan dan mengetahui strategi apa yang harus diambil untuk menurunkan emisi gas buang berdasarkan pemilihan rute distribusi untuk distribusi beras di Kota Bandung. Penelitian ini menggunakan model ILP dengan solver Matlab yang membandingkan total jarak tempuh, jumlah kendaraan, dan total biaya transportasi pada dua sistem distribusi yaitu pengiriman langsung dan pengiriman berbagi. Pada penelitian ini skenario kapasitas angkut diubah sesuai dengan penggunaan armada angkut truk jenis fuso bak, mengubah jenis truk yang memiliki kapasitas lebih besar, serta menghitung nilai emisi gas buang untuk kendaraan truk pada kedua skenario baru dan dua sistem distribusi. Hasil penelitian menunjukkan, dengan mengatur jumlah kendaraan dan total jarak tempuh minimum melalui peningkatan kapasitas angkut dan penggunaan sistem pengiriman berbagi, dapat menurunkan emisi gas buang sebesar 21,92% untuk setiap komposisinya. Kata kunci: transportasi, distribusi beras, pengiriman berbagi, reduksi emisi, emisi gas buang

Designing a Traceability System for Rice Distribution Process Using QR Code Bassed Android Application at Perum Bulog Subdivre III Surakarta

The state-owned Enterprises (SEO) that manages businesses in the food sector, especially rice is Perum Bulog. However, there were often reports from public about quality of Perum Bulog's rice. Such as the rice had contaminated with gravel or plastic and did not match with premium rice standard. Moreover, The distribution process of premium rice to outlet (RPK) found uncertainty over the arrival time of orders. It caused out of stock and lost sales at the outlet. This paper introduces a q traceability system rice distribution process based on Android with QR Code technology. Furthermore, this paper discusses the system architecture and the development of traceability system design using the company's business process data flow diagram. The developed prototype system shows the functional requirements of the system and can be used by stakeholders to monitor the production process and assist the decision-making process.

SISTEM PENDUKUNG KEPUTUSAN DALAM PENENTUAN MUTU BERAS MISKIN MENGGUNAKAN FUZZY MADM MODEL YAGER

Rice distribution for economically disadvantaged group of people is one of the main operational activities of Bulog Company to advance Indonesian society welfare. Decision making for rice quality for the addressee often became a complicated problem. Overcoming those problems takes an effective step in order to take a decision. One way to do so is to perform the classification process and search for the best result using the existing data. The use of software can be an optimal solution of the problem by using the method of Fuzzy Multi Attribute Decision Making (FMADM) Yager. This application will ease Perum Bulog to determine the best rice quality to be distributed to the economically disadvantaged group of people. After fuzzification of data to work with FMADM Yager perform pairwise comparisons are based on the value of an attribute of interest, determined the value of the weight (W), reappointment, and ranking the final results. Based on the results, then the KP. Adi Rizka an optimal alternative to the value of 0.8131 which it included in the category of suitable is 0.8. The system is built using the PHP programming language and MySQL database.

Model Transportasi dalam Meminimumkan Biaya Distribusi Beras Kemasan

Rice is a strategic commodity that a very important role as the main staple food for the majority of people in Indonesia. Rice has its own distribution development pattern that provides added value to business actors. "CV. Hidup Baru Jaya" is a company in Kupang City that is engaged in distributing packaged rice from storage warehouses to several storage warehouses in other areas. In distributing the rice, the company tries to reduce or minimize the distribution costs incurred in order to obtain optimal profit. Mathematically, the transportation model is one solution that can be used to solve this rice distribution problem. By using POM-QM V4 as the optimal solution tool, it was found that the company could distribute 125 sacks of Raja Kupang rice to the Malaka Warehouse; 150 sacks of rice to Rote Warehouse, 75 sacks to Malaka Warehouse and 200 sacks to Atambua Warehouse for Stroberry rice; Nona Timor rice was 200 sacks to Semau Warehouse, 50 sacks to Rote Warehouse and 200 sacks to Sulamu Warehouse. Thus, the company profits Rp. 20,000,000, -.

Impact Covid-19 Pandemic On Local Rice Supply Chain Flow In Kapuas Regency, Central Kalimantan, Indonesia

The fact that the pandemic condition due to Covid-19 that broke out in early 2020 has caught the attention of various elements of society. The visible impact is not only on public health, but also influences the distribution and availability of various food supplies, especially local rice in the study area. The purpose of this study was to examine the flow patterns of the local rice supply chain during the Covid-19 pandemic. Data analysis using supply chain analysis of Supply Chain management (SCM). The results of the analysis show that at the farmer / producer level it does not significantly affect farming activities, only 29.77 percent of farmers stated that there was an influence on farming activities. The impact of Covid-19 mainly affects the level of intermediary institutions in the rice distribution process. Long product (material) flow patterns by business actors need to be shortened by a short distribution route. Another effect is the inaccuracy of product arrival time due to delays in the inspection process for products brought to the research location. The impact of Covid-19 is mainly felt by distributors / wholesalers who flow products to other areas, mainly due to the increase in additional costs related to Covid-19 requirements. The solution to integrate all SCM elements through an information system can facilitate the flow pattern of local rice in Kapuas District, by intensifying the management of information related to production at the producer level, as well as controlling rice supplies at the level of intermediary institutions.

Effectiveness of Rastra Bulog Rice Distribution Using Agent Based Modeling and Simulation Tools

The Rastra Rice Program is one of the programs planned by the government to reduce the burden on target households (RTS – Rumah Tangga Sasaran). This program provides relief to the community by distributing Rastra Rice which is suitable for consumption. BULOG become one of the state-owned institutions appointed by the government to provide and distribute subsidized rice for low-income groups, the provision prioritizes the procurement of rice/rice from farmers in the country. The main objective of this research is to find a better distribution strategy so that the distribution process of Rastra rice is efficient, minimizes delays from delivery times, and minimizes the risk of storage costs. The research method used is descriptive qualitative with data collection methods using observation techniques and literature studies, while the method in determining the distribution strategy using agent-based modeling and simulation. Agent-based Model (ABM) based simulation method for Rastra rice distribution using the Multi-Agent Simulation (MASIM) stage, namely, the requirements stage, the modeling stage, the design, and architectural stage, the implementation stage, the verification stage, validation, and accreditation.