马铃薯在生长期时根系数量预测数据

可以用于马铃薯根系数量预测，输入为土壤类型、肥料使用、灌溉方式、植株高度(cm)、马铃薯茎粗(cm)、叶面积指数、根系长度(cm)、马铃薯产量（亩产量）、根系主要分布范围(cm)、根茎长(cm)、叶绿素含量（mg/g）、叶片数量。输出为马铃薯根系数量预测值。该模型帮助解决了马铃薯根系数量和马铃薯状况的关系建模的问题。马铃薯植株的根系数量对马铃薯根的生长有着重要的影响，根系的健康状况（包括有根系数量）还能影响其对养分的吸收效率，从而影响作物的最终产量。因此，通过预测马铃薯根系的数量，可以初步判断作物的生长状况‌。通过调查采集马铃薯数据并使用传统算法和多元线性回归算法预测马铃薯根系数量。该模型的输入为土壤类型、肥料使用、灌溉方式、植株高度(cm)，马铃薯茎粗(cm)，叶面积指数，根系长度(cm)，马铃薯产量（亩产量），根系主要分布范围(cm)，马铃薯根系数量，根茎长(cm)，叶绿素含量（mg/g）。多元线性回归算法通过分析这些输入变量与马铃薯根系预测数量之间的线性关系，确定每个变量的权重系数，使用深度学习框架构建模型F=ω1 * U1 + ω2* U2+…ω13 * U13，其中，ω1至ω13分别是土壤类型、肥料使用、灌溉方式、植株高度、马铃薯茎粗、叶面积指数、根系长度、马铃薯产量、根系主要分布范围、根茎长、叶绿素含量、叶片数量的权重系数，同样的 U1至 U13分别是上述13个输入量的参数值，F是马铃薯根系数量预测值。在模型训练过程中，算法会利用马铃薯根系数量实际值进行优化，调整权重系数以最小化预测误差，因此上述权重系数（ω1至ω13）是会动态变化。模型通过最小二乘法等技术，根据输入的数据计算马铃薯根系数量预测值，从而得出最终结果。通过这样的过程，模型能够将多个输入变量综合考虑准确预测根系数量。

This dataset can be used for potato root quantity prediction. Its inputs include soil type, fertilizer application, irrigation method, plant height (cm), potato stem diameter (cm), leaf area index, root length (cm), potato yield per mu, main root distribution range (cm), rhizome length (cm), chlorophyll content (mg/g), and number of leaves, with the output being the predicted value of potato root quantity.

This model addresses the problem of modeling the relationship between potato root quantity and potato growth status. Potato root quantity exerts a significant impact on root growth, and the health status of roots (including root quantity) also affects nutrient uptake efficiency, thereby influencing the final crop yield. Therefore, predicting potato root quantity enables preliminary assessment of crop growth status.

Data on potatoes were collected through field surveys, and traditional algorithms and multiple linear regression algorithms were employed to predict potato root quantity. The inputs of this model include soil type, fertilizer application, irrigation method, plant height (cm), potato stem diameter (cm), leaf area index, root length (cm), potato yield per mu, main root distribution range (cm), potato root quantity, rhizome length (cm), chlorophyll content (mg/g), and number of leaves.

The multiple linear regression algorithm analyzes the linear relationship between these input variables and the predicted potato root quantity to determine the weight coefficient of each variable. A deep learning framework is used to construct the model as F=ω₁×U₁ + ω₂×U₂ + … + ω₁₃×U₁₃, where ω₁ to ω₁₃ are respectively the weight coefficients of soil type, fertilizer application, irrigation method, plant height, potato stem diameter, leaf area index, root length, potato yield per mu, main root distribution range, potato root quantity, rhizome length, chlorophyll content, and number of leaves; while U₁ to U₁₃ are respectively the parameter values of the aforementioned 13 input quantities, and F is the predicted value of potato root quantity.

During model training, the algorithm uses the actual values of potato root quantity for optimization, adjusting the weight coefficients to minimize prediction error, so the aforementioned weight coefficients (ω₁ to ω₁₃) are dynamically changeable. The model calculates the predicted potato root quantity using techniques such as the least squares method based on the input data to obtain the final result. Through this process, the model can comprehensively consider multiple input variables to accurately predict root quantity.

搜集汇总

数据集介绍

特点

该数据集用于预测马铃薯在生长期的根系数量，包含4103条记录，每月更新。通过多元线性回归算法，模型综合考虑土壤类型、肥料使用、灌溉方式等多种因素，预测根系数量，帮助判断作物生长状况和产量。