Authors :
Mamidisetti. Helen Joyice; Katta. Valli Sri Vidya; Lankalapalli. Vijaya Lakshmi; Murala.Juilath; Ketha. Prajwala; P.Srinu Vasarao
Volume/Issue :
Volume 9 - 2024, Issue 3 - March
Google Scholar :
https://tinyurl.com/4tpjvykb
Scribd :
https://tinyurl.com/mtkje6uy
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24MAR112
Abstract :
Flood is the most devastating and destructive
that can destroy everything on land. These floods will
cause further flooding in affected areas. Flood prediction
models are being researched to reduce risk, think
strategically, reduce human life and reduce property
damage from floods. Over the last two years, AI
techniques have improved the forecasting process,
resulting in better execution and financial planning
stability. First of all, these events can take everyone's
feelings into account. Artificial intelligence models for
flood prediction are crucial for flood warning, flood
mitigation or prediction. Machine learning programs
have become ubiquitous due to their computational
needs for limited information. We believe that collecting
only a small amount of data can help representative
vector, best scores. The selected tree was successful due
to better than expected accuracy and best score. Machine
learning algorithms used in this flood prediction are
decision trees, logistic regression, etc. For evaluation and
comparison. Logistic regression can provide more
accurate results than other algorithms and provide high
efficiency and improvement. Floods are perhaps the
most destructive event in the world, can cause
irreversible damage and cause great suffering to
humanity. Generally, most farmers are the most
disturbed people in the world because their hard work
can suddenly fail, causing their hearts to become
melancholy. To measure water level and velocity over a
large area, it is important to provide an exposure model
that includes safety. These models can be aimed to
improve the prediction by using different methods.
Additionally, these models provide accurate predictions
of flood events in a year, but do not provide much
understanding and detail of the options needed.
Keywords :
Forecast, Flood Forecast, ML Model, Flood Decision, Flood Research, Expiration Date.
Flood is the most devastating and destructive
that can destroy everything on land. These floods will
cause further flooding in affected areas. Flood prediction
models are being researched to reduce risk, think
strategically, reduce human life and reduce property
damage from floods. Over the last two years, AI
techniques have improved the forecasting process,
resulting in better execution and financial planning
stability. First of all, these events can take everyone's
feelings into account. Artificial intelligence models for
flood prediction are crucial for flood warning, flood
mitigation or prediction. Machine learning programs
have become ubiquitous due to their computational
needs for limited information. We believe that collecting
only a small amount of data can help representative
vector, best scores. The selected tree was successful due
to better than expected accuracy and best score. Machine
learning algorithms used in this flood prediction are
decision trees, logistic regression, etc. For evaluation and
comparison. Logistic regression can provide more
accurate results than other algorithms and provide high
efficiency and improvement. Floods are perhaps the
most destructive event in the world, can cause
irreversible damage and cause great suffering to
humanity. Generally, most farmers are the most
disturbed people in the world because their hard work
can suddenly fail, causing their hearts to become
melancholy. To measure water level and velocity over a
large area, it is important to provide an exposure model
that includes safety. These models can be aimed to
improve the prediction by using different methods.
Additionally, these models provide accurate predictions
of flood events in a year, but do not provide much
understanding and detail of the options needed.
Keywords :
Forecast, Flood Forecast, ML Model, Flood Decision, Flood Research, Expiration Date.
