A Comparative Study between Frequency Ratio Model and Gradient Boosted Decision Trees with Greedy Dimensionality Reducti
- PDF / 2,411,000 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 46 Downloads / 170 Views
A Comparative Study between Frequency Ratio Model and Gradient Boosted Decision Trees with Greedy Dimensionality Reduction in Groundwater Potential Assessment Shruti Sachdeva 1
& Bijendra Kumar
1
Received: 4 March 2020 / Accepted: 16 September 2020/ # Springer Nature B.V. 2020
Abstract
Khammam district in Telangana, India has gained notoriety for the increasing number of farmer suicides attributed to the augmenting crop failures. Climate change, causing sporadic and uneven rains in the largely agricultural state has increased the strain on the already dwindling water table. Hence, there is a need for an in-depth analysis into the current state of these resources for their sustainable utilization. This study deploys 21 factors for predicting the groundwater potential of the region. An inventory of 126 wells was utilized to construct the dataset with the influencing factors. The statistical method of Frequency ratio (FR) and a machine learning (ML) approach of Gradient Boosted Decision Trees with Greedy feature selection (GA-GBDT) have been applied. GA-GBDT model (accuracy: 81%) outperformed the FR model (accuracy: 63%) and it was deduced that ML has the capability to perform equally well and even better than the traditional statistical approaches in similar studies. The models were utilized to generate groundwater potential maps for the region. The FR model predicted 78 sq.km as having a very high potential to yield groundwater, while GA-GBDT estimated it to be 152 sq.km. The results could play a vital role in irrigation management and city planning. Keywords Groundwater potential assessment . Machine learning . Dimensionality reduction . Gradient boosted decision trees
* Shruti Sachdeva [email protected] Bijendra Kumar [email protected]
1
Department of Computer Science and Engineering, Netaji Subhas University of Technology, New Delhi, India
Sachdeva S., Kumar B.
1 Introduction Water in phreatic zone, pooling in confined or unconfined aquifers below the earth’s surface, contributes to the underground water table. This latent reservoir constitutes approximately 98% of unfrozen freshwater in the world (UNESCO-IHP 2019). Unsurprisingly, groundwater is responsible for meeting more than 50% of demands for drinking-water, globally. With earth’s continental crust providing a natural barrier to these fragile ecosystems, there is a natural immunity enveloping these precious resources that maintains them in their relatively pure form. Coupled with the water’s superior quality, these have a high resilience and reliability in terms of quantity as well. These qualities render them as a viable source for extraction at modest developmental expenditures. Unfortunately, rapid urbanization, rise in population and modifications in the land use patterns has endangered this valuable resource. The fact that there has been a 300% increment in groundwater extraction, in the past fifty years, holds testimony to the precarious state of affairs (GRAPHIC 2015). Saltwater contamination of groundwater, land subsidence and a l
Data Loading...
