Data Partitioning and Machine Learning Techniques for Lake Level Forecasting: A Survey |
Author(s): |
| Manali Shukla , Rungta College of Engineering and Technology Bhilai (C.G.), India; Megha Seth, Rungta College of Engineering and Technology Bhilai (C.G.), India |
Keywords: |
| Regression; Hadoop; K-Means; ARIMA |
Abstract |
|
Lakes are lively system those are insightful to confined climate and to land-use amendment in the neighboring site. Several lakes obtain their water primarily from rainfall, some are conquered by drainage overspill, and several others are illicit by land water systems. As time grows, the areal amount and profundity of water in lakes are indication of effect in climatic factors some of them are rainfall, emission, temperature, and airstream speed. Fluctuations of lake level diverge with the water equilibrium of the lake and their catchment, and might be, in assured cases, reflect changes in shallow groundwater resources. Prevalent surface fresh water system on the globe. The seasonal, monthly and yearly surface water level of the lakes alters in retort to an assortment of factors. In this paper we have discussed some bottleneck of k-means clustering technique and discussed prediction model for lake level forecasting. |
Other Details |
|
Paper ID: IJSRDV4I31579 Published in: Volume : 4, Issue : 3 Publication Date: 01/06/2016 Page(s): 1930-1934 |
Article Preview |
|
|
|
|
