Muhamad Rafi Ramdhani, . (2026) IMPLEMENTASI ALGORITMA LSTM PADA SISTEM REKOMENDASI WAKTU TANAM PADI BERBASIS WEBSITE MENGGUNAKAN DATA KLIMATOLOGI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (216kB) |
|
Text
AWAL.pdf Download (859kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (281kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (684kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (559kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB V.pdf Download (246kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (263kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (96kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (40MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
Unpredictable climate change has made determining planting time, managing irrigation, and selecting appropriate rice varieties less effective, thereby reducing productivity and increasing the risk of crop failure. In addition, the available climatological data have not been optimally utilized because the information provided is generally technical and difficult to apply directly to cultivation decision-making. This study aimed to design and develop a website based on the Long Short-Term Memory (LSTM) algorithm to generate climate predictions and provide recommendations for planting time, water requirements, and suitable rice varieties. The website was developed using the Rapid Application Development (RAD) method, while the prediction models were built using BMKG’s climatological data from the Bogor region and integrated into the website through a Flask API. Planting time recommendations were generated using Fuzzy Sugeno logic based on the predicted climatological conditions. The evaluation results showed that the temperature model achieved an MAE of 0.67383 and an RMSE of 0.86260, the humidity model achieved an MAE of 3.10620 and an RMSE of 3.93650, the rainfall regression model achieved an MAE of 10.01678 and an RMSE of 17.56947, while the rainfall classification model achieved an accuracy of 80.321%. The Black Box Testing results indicated that all website functions operated as expected, while the User Acceptance Testing (UAT) achieved an average score of 4.37 out of 5. Therefore, this study successfully developed a website capable of supporting decision-making in rice cultivation based on climatological data. Keywords: climatological data, deep learning, LSTM algorithm, rice, website.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2210511019] [Pembimbing 1: Muhammad Adrezo] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Jayanta] [Penguji 2: Nindy Irzavika] |
| Uncontrolled Keywords: | climatological data, deep learning, LSTM algorithm, rice, website |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software S Agriculture > S Agriculture (General) S Agriculture > SB Plant culture T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | MUHAMAD RAFI RAMDHANI |
| Date Deposited: | 28 Aug 2026 06:20 |
| Last Modified: | 28 Aug 2026 06:20 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52445 |
Actions (login required)
 |
View Item |