Tehisaru aitab Eesti teadlastel kaardistamata kuivenduskraave tuvastada

Tehisaru aitab Eesti teadlastel kaardistamata kuivenduskraave tuvastada

EN

Artificial Intelligence Helps Estonian Scientists Identify Unmapped Drainage Ditches

Tartu Ülikooli teadlased kasutasid tehisaru, et leida kuivenduskraave. See aitab paremini mõista maastikku ja keskkonda.

EN

Scientists from the University of Tartu used artificial intelligence to find drainage ditches. This helps to better understand the landscape and environment.

Eestis on palju . Need aitavad ära juhtida liigvett põldudelt ja metsadest. Kui kraavid ei tööta, võib see ja puid.
EN

There are many drainage ditches in Estonia. They help to remove excess water from fields and forests. If the ditches do not work, it can damage crops and trees.

Kuivenduskraavid mõjutavad ka keskkonda. Näiteks suurendavad nad a. Seetõttu on oluline teada, kus kraavid asuvad.
EN

Drainage ditches also affect the environment. For example, they increase the amount of greenhouse gases. Therefore, it is important to know where the ditches are located.

Traditsiooniliselt on kraave . See on aga aeganõudev, eriti metsades. Tehisaru aitab seda teha kiiremini ja täpsemalt.
EN

Traditionally, ditches have been mapped manually. However, this is time-consuming, especially in forests. Artificial intelligence helps to do this faster and more accurately.

Tehisaru kasutab it. Selle abil saab tuvastada kraavid, mis on kitsad ja taimestikuga kaetud. Tartu Ülikooli teadlased kasutasid it U-Net, mis on väga täpne.
EN

Artificial intelligence uses a terrain elevation model. This allows identifying ditches that are narrow and covered with vegetation. Scientists from the University of Tartu used the deep learning method U-Net, which is very accurate.

Mudelit tuli eelnevalt treenida. Selleks kasutati Rootsi andmeid. Seejärel kohandati mudelit Eesti andmetega. Treenimiseks võeti andmed metsadest, põldudest ja elt.
EN

The model had to be trained beforehand. For this, Swedish data was used. Then the model was adapted to Estonian data. Data from forests, fields, and peatlands were used for training.

Tehisaru leidis palju uusi kraave. Kokku leiti ligi 45 000 kilomeetrit kraave juurde. Mudel oli kõige täpsem el, kus taimestikku pole. Metsades oli mudel vähem täpne, sest puud segavad tuvastamist.
EN

Artificial intelligence found many new ditches. In total, nearly 45,000 kilometers of ditches were found. The model was most accurate in peatlands where there is no vegetation. In forests, the model was less accurate because trees interfere with detection.

Uuring näitab, et võib olla väga kasulik. See aitab kiiresti ja väheste andmetega leida kraave. See on oluline keskkonna ja maastiku mõistmiseks.
EN

The study shows that artificial intelligence can be very useful. It helps to quickly find ditches with little data. This is important for understanding the environment and landscape.