Spatial modelling of soil nutrients using random forest algorithm (Record no. 6532)

MARC details
000 -LEADER
fixed length control field 02183nam a22001937a 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220107122852.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 190628b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Transcribing agency IIITMK
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Aparna T M (92317006)
9 (RLIN) 16006
245 ## - TITLE STATEMENT
Title Spatial modelling of soil nutrients using random forest algorithm
300 ## - PHYSICAL DESCRIPTION
Extent MSC GIS 2017-2019
500 ## - GENERAL NOTE
General note Machine learning techniques for predictions are very common nowadays.<br/>But spatial predictions are not as common as normal prediction. Spatial<br/>predictions can be done by using different Machine learning algorithms.<br/>The study was proposed to predict spatial distribution of five soil nutrients<br/>based on the Random Forest algorithm.Random forest is a machine<br/>learning algorithm used here for spatial prediction. Spatial autocorrelation<br/>techniques are sometimes biased and this is suboptimal. This<br/>study presents a random forest for spatial predictions where buffer<br/>distances from observed spatial points that are used as explanatory<br/>variables. It incorporates geographical proximity effects into the prediction<br/>process. The result shows that random forest can obtain equally accurate<br/>and unbiased predictions as different versions of kriging. Advantages of<br/>using random forest over kriging are that it needs no rigid statistical<br/>assumptions about the distribution of the target variable. It gives more<br/>informative maps. It is less biased than kriging. Random forest framework<br/>for spatial prediction is more accurate because it trains an amount of data<br/>and prediction is done by using that trained data. There are some<br/>disadvantages also for random forest,its exponentially growing<br/>computational intensity with increase of calibration data and covariates.<br/>The high sensitivity of predictions to input data quality is also a<br/>disadvantage. Random forest’s success is because of its training data<br/>quality, especially its spatial data sampling quality.It minimizes<br/>extrapolation problems and any type of bias in data.
502 ## - DISSERTATION NOTE
Degree type MSC GIS
Name of granting institution 2017-2019
Year degree granted INT
-- Radhakrishnan T
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element SPATIAL PREDICTION
9 (RLIN) 16007
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element RANDOM FOREST ALGORITHM
9 (RLIN) 16008
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element MACHINE LEARNING ALGORITHM
9 (RLIN) 16009
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Collection code Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type
    Dewey Decimal Classification     Non Fiction IIITM-K Kerala University of Digital Sciences, Innovation and Technology Knowledge Centre   28/06/2019   R-1528 28/06/2019 28/06/2019 Project Reports