The current condition of the Karangantu Archipelago Fisheries Port (PPN) is still considered unfavorable because the operational area of ??the port waters looks dirty and shabby. There are many ships that are no longer used in the Karangantu PPN operational area. Based on the results of interviews with PPN Karangantu officers, there are several things that cause ships to be abandoned in the operational area of ??PPN Karangantu waters, including the age of the ship, costs or capital, and human resources. Abandoned ships that are not immediately handled will result in obstacles to the flow of water traffic at the port and create a risk of collision for other ships passing by. Therefore, web-based mapping of abandoned ships (WebGIS) is needed in the operational area of ??PPN Karangantu waters. It is hoped that the results of this abandoned ship mapping can be used by the port to report abandoned ships to the center so that they can immediately take action to transport the abandoned ships. With the existence of WebGIS mapping abandoned ships, the port does not need to go directly to the field to find the location of abandoned ships because the information can be accessed via the web that has been created. Data collection on coordinate points was carried out by field survey and tagging using the GPS Map Camera application. The research results show that there are 74 abandoned ships in the Karangantu PPN operational area.

Accurate weather forecasts play an important role in today's world as various sectors such as marine, navigation, agriculture and industry are basically dependent on weather conditions. Weather forecasts are also used to predict the occurrence of natural disasters. Weather forecasting determines the exact value of weather parameters and then predicts future weather conditions. In this study the parameters used are. Different weather parameters were collected from the Serang Maritime Meteorological Station and then analyzed using a neural network-based algorithm, namely Long-short term memory (LSTM). In predicting future weather conditions using LSTM neural networks are trained using a combination of different weather parameters, the weather parameters used are temperature, humidity, rainfall, and wind speed. After training the LSTM model using these parameters, future weather predictions are performed. The prediction results are then evaluated using RMSE. Prediction results show that the model is more accurate when predicting temperature data with RMSE 0.37, then RMSE wind speed 0.72, RMSE sunlight 2.79, and RMSE humidity 5.05. This means that the model is very good at studying weather data, inversely proportional to humidity data.