Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{157209,
        author = {Rohini and Harjinder Kaur},
        title = {Soil fertility detection using remote images},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {6},
        pages = {300-307},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=157209},
        abstract = {Soil fertility in terms of incorrect crop sow in soil often led to economic, and human loses. Early predictions corresponding to soil fertility can allow administration to take preventive and precautionary measures Soils are common and uncertain soil fertility that can occur due to disturbance in normal slope stability. Soils often accompany earthquakes, rain, or eruptions.  This research proposed an early warning system for soil. Entire framework associated with proposed system consists of sensor, fog and cloud layer. Data acquisitions employed within sensor layer collects the data about the soil and land through sensors. Furthermore, pre-processing will be performed at sensor layer. Pre-processing mechanism remove any noise from the dataset. Fog layer contains feature reduction mechanism that is used to reduce the size of data to conserve energy of sensors during transmission of data. Furthermore, predictor variables selected within energy conservation mechanism will be used for exploratory data analysis (EDA). Main characteristics of data will be extracted using EDA. Furthermore, principal component analysis applied at fog layer analyses the dependencies between the attributes. Dependencies are calculated using correlation. Negatively skewed attributes will be rejected thus dimensionality of dataset is reduced further. All the gathered prime attributes are stored within cloud layer. K means clustering is applied to group the similar entities within same cluster. This step will reduce the overall execution time of prediction. Formed clusters are fed into ARIMA(Auto regressive integrated moving averages) for predictions. Relevant authorities can fetch the result by logging into the cloud. The effectiveness of proposed approach is proved at different levels using metrics such as classification accuracy and F-score. },
        keywords = {Fog computing, soil prediction, energy efficiency, K means clustering, PCA, ARIMA},
        month = {},
        }