| CPC G06Q 50/02 (2013.01) [A01C 21/007 (2013.01)] | 6 Claims |
|
1. A method for recommending rice panicle fertilizer nitrogen based on crop growth models and remote sensing coupling, comprising the following steps:
step S1: constructing a basic database, comprising:
obtaining a multi-year and multi-point aboveground biomass and plant nitrogen concentration data during a key growth period of rice, multi-source remote sensing data during the key growth period of rice, nitrogen application amount data for each plot before panicle fertilizer in target years, plot vector layer data in a study area and a decision support system for agrotechnology transfer (DSSAT) parameter adjustment database, to build the basic database;
wherein the key growth periods of rice include: tillering stage, panicle initiation stage and stem elongation stage;
wherein said multi-source remote sensing data during the key growth period of rice includes satellite image data and unmanned aerial vehicles (UAV) image data, including multi-year historical data and target years data;
step S2: constructing agronomic parameter inversion modeling based on remote sensing a vegetation index, comprising:
step S2.1: extracting spectral reflectance data of satellite image data and UAV image data of experimental points in the key growth period of rice obtained in the step S1, and using the spectral reflectance data of the satellite image data and UAV image data to calculate the vegetation index;
step S2.2: using a linear regression model, nearest neighbor model r, decision tree model, support vector machine and random forest model of a machine learning library, to construct relationship models of each vegetation index obtained in the step S2.1, with the aboveground biomass and plant nitrogen concentration, the optimal model is screened through model evaluation indicators, and optimal inversion models of the aboveground biomass and the plant nitrogen concentration based on satellite remote sensing and the optimal inversion models of the aboveground biomass and plant nitrogen concentration based on UAV remote sensing are obtained respectively;
step S3: performing a rice nitrogen nutrition diagnosis based on nitrogen nutrition index, comprising:
step S3.1: using a geospatial data abstraction library to respectively apply the aboveground biomass and plant nitrogen concentration optimal inversion models based on satellite remote sensing and UAV remote sensing obtained in the step S2 to the satellite image data and UAV image data of the target years, to obtain aboveground biomass and plant nitrogen concentration estimation layers based on satellite remote sensing and UAV remote sensing;
step S3.2: calculating the aboveground biomass and the plant nitrogen concentration estimation layers based on satellite remote sensing and UAV remote sensing obtained in the step S3.1 based on a rice nitrogen dilution curve, obtain the nitrogen nutrition index layer based on satellite remote sensing and the nitrogen nutrition index layer based on UAV remote sensing;
wherein the critical nitrogen concentration is calculated, as follows:
 wherein nitrogen nutrition index (NNI) is calculated, as follows:
NNI=Na/Nc;
wherein, Nc is the critical nitrogen concentration, whose unit is g kg−1; AGB is the aboveground biomass, whose unit is t ha−1; a and b are the nitrogen dilution curve coefficients; Na is plant nitrogen concentration, whose unit is g kg−1;
step S3.3: using a regional analysis tool in combination with the vector layer of the study area plots obtained in the step S1, to separately process the aboveground biomass and plant nitrogen concentration estimation layers based on satellite remote sensing and the aboveground biomass and plant nitrogen concentration estimation layers based on UAV remote sensing obtained in the step S3.1 as well as the nitrogen nutrition index layer based on satellite remote sensing and the nitrogen nutrition index layer based on UAV remote sensing obtained in the step S3.2, to obtain the plots-level nitrogen nutrition index estimation layer and plots-level aboveground biomass and plant nitrogen concentration estimation layers based on satellite remote sensing, and plots-level nitrogen nutrition index estimation layers and plots-level aboveground biomass and plant nitrogen concentration estimation layers based on UAV remote sensing;
step S3.4: judging the nitrogen nutrition status of each plot in the plots-level nitrogen nutrition index estimation layer obtained from each remote sensing source in the step S3.3 based on the nitrogen nutrition index threshold range;
wherein NNI<0.95 means nitrogen deficiency, 0.95<NNI<1.05 means nitrogen is suitable, and NNI>1.05 means nitrogen is sufficient;
step S4: calculating recommendation of panicle fertilizer nitrogen, comprising
step S4.1: localizing genetic parameters of a rice growth model, comprising:
inputting the data in the DSSAT parameter adjustment database obtained in the step S1 into the rice growth model, continuously adjusting the genetic coefficient of the model to approach to a measured value through DSSAT-GLUE (Decision Support System for Agrotechnology Transfer-Generalized Likelihood Uncertainty Estimation) and trial-and-error methods; wherein genetic parameters are localized genetic parameters, and the rice growth model is a localized model;
step S4.2: using the regional analysis tool to extract raster values of the plot-level aboveground biomass and plant nitrogen concentration estimation layers of each remote sensing source obtained in the step S3.3 to obtain an estimated aboveground biomass and plant nitrogen concentration values of each remote sensing source in each plot, calculate PNUdifference in each remote sensing source each plot, the difference in plants nitrogen absorbing amount in each source each plot is PNUdifference, and the plot-level aboveground biomass estimate of each remote sensing source is input into the localized rice growth model obtained in the step S4.1, to obtain plot-level target yield and total recommended nitrogen application rate at middle stage of rice growth of each remote sensing source;
wherein the plants nitrogen absorbing amount is calculated, as follows:
PNU=Na×AGB;
wherein the plants critical nitrogen absorbing amount is calculated according to:
PNUC=Nc×AGB;
wherein the difference in plants nitrogen absorbing amount is calculated, as follows:
PNUdifference=PNU−PNUc;
wherein PNU is the plants nitrogen absorbing amount, whose unit is kg ha−1; PNUC is the plants critical nitrogen absorbing amount, whose unit is kg ha−1; PNUdifference is the difference in plants nitrogen absorbing amount, whose unit is kg ha−1; AGB is the aboveground biomass, whose unit is t ha−1; Nc is the critical nitrogen concentration, whose unit is g kg−1; Na is the plant nitrogen concentration, whose unit is g kg−1;
step S4.3: combining the plot-level target yield and total recommended nitrogen application amount of each remote sensing source obtained in the step S4.2, and the nitrogen application amount data of each plot before panicle fertilizer in the target year, calculate the recommended nitrogen amount of panicle fertilizer in each plot of each remote sensing source, and finally obtaining recommendations of panicle fertilizer nitrogen at the plots-level of each remote sensing source;
the recommended amount of nitrogen fertilizer for each plot=(total recommended nitrogen application amount−nitrogen application amount before panicle fertilizer)−PNUdifference/nitrogen recovery rate of panicle fertilizer.
|