A Data-Driven Approach to Soil Moisture Collection and Prediction

Hong, Zhihao; Kalbarczyk, Zbigniew; Iyer, R.K.

doi:10.1109/smartcomp.2016.7501673

Cited by 31 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SM prediction at 1‐ and 2‐m depth demonstrated good performance with high explained variations (0.88 and 0.97). Hong, Kalbarczyk, and Iyer () used the RVM and SVM models for generating nine site‐specific models to forecast SM with 1‐ and 2‐day lagged meteorological parameters (air temperature, relative humidity, wind speed, solar radiation, precipitation, and soil temperature at depth 10 and 20 cm) and SM as inputs. The results showed SM prediction across nine different locations at depth 5 cm achieved good performance, and the obtained R 2 values of RVM and SVM were 0.92 and 0.95.…”

Section: Introductionmentioning

confidence: 99%

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Pan

Shangguan

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

Soil moisture (SM) is a key variable of land surface‐atmosphere interactions. Data‐driven methods have been used to predict SM, but the predictability of SM has not been well evaluated. This study investigated what variables and methods can be used to better predict SM for leading times of 7 days or longer with a global coverage of FLUXNET site data for the first time. Three machine‐learning models, that is, Bayesian linear regression, random forest, and gradient boosting regression tree, are used for the prediction. Variables including atmospheric forcing, surface soil temperature, time variables (year, day of year, and hour), the Fourier transformation of time variables, and lagged SM (7‐ to 14‐day lagged) were sequentially added into models. A framework with five experiments is designed for factorial exploration of SM predictability. A stepwise method was used to build the best models for each site. The performance of regression models became better when adding more explaining variables in most cases. The results showed that from 50 to 95% of variation of the best models can be explained. The important explaining variables are lagged surface SM, followed by day of year, year, soil temperature, and atmospheric forcing. The predictability of SM depends highly on SM memory characteristics and the persistence of seasonality. The effect of SM memory characteristics on SM prediction as an initial condition question has been widely discussed in this paper. Our results also provide an insight that mechanisms of seasonality effects on SM should be also paid more attention to.

show abstract

Section: Introductionmentioning

confidence: 99%

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Pan

Shangguan

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…Zhihao et al [5] uses SVM techniques and RVM techniques to forecast the moisture of the soil. They uses some electronic devices for this namely "MicaZ mote" and "VH400".…”

Section: Literature Surveymentioning

confidence: 99%

Crop Yield Prediction using XG Boost Algorithm

Ravi*,

Baranidharan

2020

IJRTE

View full text Add to dashboard Cite

The main objective of this research is to predict crop yields based on cultivation area, Rainfall and maximum and minimum temperature data. It will help our Indian farmers to predict crop yielding according to the environment conditions. Nowadays, Machine learning based crop yield prediction is very popular than the traditional models because of its accuracy. In this paper, linear regression, Support Vector Regression, Decision Tree and Random forest is compared with XG Boost algorithm. The above mentioned algorithms are compared based on R2 , Minimum Square Error and Minimum Absolute Error. The dataset is prepared from the data.gov.in site for the year from 2000 to 2014. The data for 4 south Indian states Andhra Pradesh, Karnataka, Tamil Nadu and Kerala data alone is taken since all these states has same climatic conditions. The proposed model in this paper based on XG Boost is showing much better results than other models. In XG Boost R2 is 0.9391 which is the best when compared with other models.

show abstract

“…The shopping process, bill and order details will be notified to the user. The research by W. Fan, C. Chong, G. Xiaoling, Y. Hua and W. Juyun [6] is about predicting crop yield using big data analytics. The paper overcomes the failure of previous algorithm to handle massive data by using big data.…”

Section: Literature Surveymentioning

confidence: 99%

Assessment Framework Modeling using Location Aware Computing for Fertilizer Management and Crop Recommendation

Alex¹,

Kanavalli²

2019

IJRTE

View full text Add to dashboard Cite

Indian economy mainly depends on the agriculture, which contributes a major part in the growth and development of the nation. This is directly connected to the standard of life of farmers which covers more than 40 percent of the country population. Looking at the current situation of agriculture in India, agricultural productivity in India is not competitive to the world standards. For increasing the crop productivity farmers are forced to use more fertilizers which will end in health risk for the consumers. Lack of a proper knowledge of the effective usage of fertilizers and the changing soil nutrient values are the major problems for a farmer apart from the loss due to climate change and so many other factors. To address the problem , we propose to build an application model 'Prediction On Fertilizer Management for Crop Productivity' which enables the farmers to understand and effectively utilize their money with effective methods of seasonal crops production by providing recent and intimate information about which has to be produced, soil suitability, its nutrient values and soil moisture level which pasteurization management methods, how to apply the fertilizers in larger areas, what amount of water must be given, how to develop a model maps to the current scenario of farm areas. Crop Yield Production is basically an aggregation of crop and fertilizer recommendation, soil analysis, and crop yield calculations based on recent market scenario. Through our model we are revising and correcting the existing system with predictive analytics of the usage of effective fertilizers with less health risk.

show abstract

A Data-Driven Approach to Soil Moisture Collection and Prediction

Cited by 31 publications

References 12 publications

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Crop Yield Prediction using XG Boost Algorithm

Assessment Framework Modeling using Location Aware Computing for Fertilizer Management and Crop Recommendation

Contact Info

Product

Resources

About