Soil Moisture Retrieval using Ground Water Dataset using Machine Learning
In this project work we perform analysis of groundwater level data in three districts of Tamilnadus. We have analysed this data for more than 100 observation wells in each of these districts and developed seasonal models to represent the groundwater behaviour. Three different type of models were developed-periodic, polynomial and rainfall models. While periodic and polynomial models capture trends on water levels in observation wells, the rainfall model explores the correlation between the rainfall levels and water levels. The periodic and polynomial models are developed only using the groundwater level data of observation wells while the rainfall model also uses the rainfall data. All the data and the models developed with a summary of analysis is available at . The larger aim is to build these models to predict temporal changes in water level to aid local water management decisions and also give region specific input to Government planning authorities e.g. Groundwater Survey and Development Agency to flag water status with more information.
Water below the land surface appears in two zones – saturated and the unsaturated zone. When rainfall occurs, a part of it infiltrates into the ground. Some amount of this infiltrated rain is held up by the upper layer of soil in its pore spaces. This layer is immediately below the land surface and contains both air and water and is known as the unsaturated zone. When all the soil pores are completely filled with water, then water seeps further down through the fractures in the rock. After a certain depth all pores in the soil are completely filled with water, this part forms the saturated zone. The top of saturated zone is known as the water table and water in this zone is called the groundwater.
Groundwater level is an indicator of groundwater availability, groundwater flow, and the physical characteristics of an aquifer or groundwater system. Due to increased population and decreased groundwater recharge, the demand increases and it may not be feasible to check the draft of groundwater resources. The only available option is to increase the recharge rate to the aquifer by suitable means. Therefore it is necessary to quantify the present rate of groundwater recharge, monitor the change in water table depth and then predict the future trend of water table depth before any intervention.
- Any phenomenon, which produces pressure change within an aquifer, results into the change of ground water level.
- These changes in ground water level can be a result of changes in storage, amount of discharge and recharge, variation of stream stages and evaporation.
This is mainly in the form of estimation of the magnitude of a hydrological parameters. The factors that influence and control the groundwater level fluctuation were determined to develop a forecasting model and examine its potential in predicting groundwater level. Models for prediction of water table depth were developed based on Artificial Neural Networks (ANN) with different combinations of hydrological parameters. The best combination was confirmed with factor analysis. The input parameters for groundwater level forecasting were derived using Time Series Analysis (TSA).
- Most of the researches used ANN alone to predict groundwater level.
- But the present study incorporated factor analysis along with time series forecasting to increase the accuracy and usefulness of prediction.
Soil Moisture Retrieval using Machine Learning
Field survey was carried out to establish the observation well locations suitable for the study area. The wells were selected in such a way that areas of different elevations are suitably covered. The spatial locations were identified by conducting GPS (Global positioning system) survey. The groundwater level was recorded periodically.
In factor analysis the correlation between input parameters Potential evapotranspiration (PET), temperature, humidity and rainfall were analysed using Statistical Package for Social Sciences (SPSS) for monsoon and non-monsoon season. Any factor having component value less than 0.5 was extracted as it is less significant for the input combination.
Time series analysis (TSA):
In this phase the input parameters required for the prediction of groundwater level were forecasted. The values were forecasted based on previously observed data. In this study, time series analysis based on moving average method was adopted.
Prediction using ANN:
ANN is an information processing paradigm inspired by biological nervous systems, such as our brain. It consists of large number of highly interconnected processing elements, called neurons, working together. An ANN consists of input, hidden and output layers as shown in Fig 1 and each layer includes an array of processing elements. A Neural network is characterized by its architecture that represents the pattern of connection between nodes, its method of determining the connection weights, and the activation function. The learning, training, performance and transfer functions used in this study are LEARNGDM, TRAINSCG, MSE AND TRANSIG respectively.
0.00 average based on 0 ratings
More Things You Might Like This
Abstract: Although the educational level of the Portuguese population has improved in the last decades, the statistics keep Portugal at Europe’s tail end due to its high student failure rates. In particular, lack of success in the core classes of Mathematics and the Portuguese language is extremely serious. On the other hand, the fields of
Abstract: Advances in natural language processing (NLP) and educational technology, as well as the availability of unprecedented amounts of educationally-relevant text and speech data, have led to an increasing interest in using NLP to address the needs of teachers and students. Educational applications differ in many ways, however, from the types of applications for which
Machine Learning based Regression Model for Prediction of Soil Surface Humidity over Moderately Vegetated Fields
Abstract: Agriculture is one of the major revenue producing sectors of India and a source of survival. Numerous seasonal, economic and biological patterns influence the crop production but unpredictable changes in these patterns lead to a great loss to farmers. These risks can be reduced when suitable approaches are employed on data related to soil