CNN and LSTM Approach for Soil Nutrient analysis for Sugarcane Crop

Author:

J Kavitha K1,K Krishna Prasad2

Affiliation:

1. GMIT

2. Srinivas University

Abstract

Abstract

A new paradigm has been adopted in agricultural techniques, tools, and technology. To guarantee the implementation of site-specific crop management, which includes soil nutrient treatments according to crop requirements, precision agriculture is crucial. Soil nutrients are a major component in determining the growth of precision agriculture, which has gained global attention. One of the main challenges is more effective nutrient content detection as it guides well-planned nutrient-level-boosting routines. Many approaches, such using research labs and additional mobile labs, haven't shown to be very useful in helping farmers control their soil fertility. Taking advantage of the breakthroughs is severely hampered by factors like lack of knowledge and distance from research centers. In the work proposed, LSTM based RNN is employed to predict the Ph and nutrient values of the soil measured through microcontroller using sensor from the agricultural field. At the same time, RELU-CNN approach is applied to the soil images for measuring the same values. The values obtained from both the approaches are compared against each other so that the method may be made directly available to the farmers for evaluating the nutrient level of the soil and take necessary action. The approaches are measured in terms of quality parameters Recall, F1-Score, Accuracy, Precision and RMS value.

Publisher

Springer Science and Business Media LLC

Reference15 articles.

1. Lu G, Wang S, Lian Y, Wei Y (2020) Development and utilization of sugarcane by-products in the sugar manufacturing process,Sugar Crop, Vol. 42, pp. 75–80,

2. Pang Z, Tayyab M, Kong C, Liu Q, Liu Y, Hu C et al (2008) Continuous Sugarcane Planting Negatively Impacts Soil Microbial Community Structure, Soil Fertility, and Sugarcane Agronomic Parameters, Microorganisms, 9, 2021. https://doi.org/10.3390/microorganisms9102008

3. Sudhir Madhav Patil, Sugarcane Disease Detection Using CNN-Deep Learning Method: An Indian Perspective;Upadhye SA;Univers J Agricultural Res,2023

4. Sammy V, Militante BD, Gerardo NV, Dionisio (2019) Plant Leaf Detection and Disease Recognition using Deep Learning, Proceeding of the IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), Yunlin, Taiwan, 2019(2019), pp. 579–582,

5. Reddy GM, Ramana PHV, Anusha P, Chakravarthy BK, Kasukurthi A, Lakshmi VS, A Survey on Sugarcane Leaf Disease Identification Using Deep Learning Technique(CNN) (2023) Int J Recent Innov Trends Comput Communication 11(5):248–254. https://doi.org/10.17762/ijritcc.v11i5.6611

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3