亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于Self-Attention-BiLSTM網(wǎng)絡(luò)的西瓜種苗葉片氮磷鉀含量高光譜檢測(cè)方法
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:

國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2019YFD1001901)、湖北省重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2021BBA239)、HZAU-AGIS交叉基金項(xiàng)目(SZYJY2022006)、中央高校基本科研業(yè)務(wù)費(fèi)專項(xiàng)資金項(xiàng)目(2662022YLYJ010)和國(guó)家西甜瓜產(chǎn)業(yè)技術(shù)體系項(xiàng)目(CARS-25)


Hyperspectral Non-destructive Detection of Nitrogen, Phosphorus and Potassium Content of Watermelon Seedling Leaves Based on Self-Attention-BiLSTM Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    元素含量無(wú)損檢測(cè)技術(shù)可以為植物生長(zhǎng)發(fā)育的環(huán)境精準(zhǔn)調(diào)控提供關(guān)鍵實(shí)時(shí)數(shù)據(jù)。以西瓜苗為例,提出了一種基于圖譜特征融合的氮磷鉀含量深度學(xué)習(xí)檢測(cè)方法。首先,使用高光譜儀拍攝西瓜苗葉片的高光譜圖像,使用連續(xù)流動(dòng)化學(xué)分析儀測(cè)定葉片的3種元素含量。然后,采用基線偏移校正(BOC)疊加高斯平滑濾波(GF)的光譜預(yù)處理方法和隨機(jī)森林算法(RF)建立預(yù)測(cè)模型,基于競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)采樣(CARS)和連續(xù)投影算法(SPA) 2種算法初步篩選出特征波長(zhǎng),再綜合考慮波長(zhǎng)數(shù)和建模精度設(shè)計(jì)了一種最優(yōu)波長(zhǎng)評(píng)價(jià)方法,將波長(zhǎng)數(shù)進(jìn)一步減少到3~4個(gè)。最后,提取使用U-Net網(wǎng)絡(luò)分割的彩色圖像顏色和紋理特征,和光譜反射率特征一起作為輸入,基于自注意力機(jī)制-雙向長(zhǎng)短時(shí)記憶(Self-Attention-BiLSTM)網(wǎng)絡(luò)構(gòu)建了3種元素含量的預(yù)測(cè)模型。實(shí)驗(yàn)結(jié)果表明,氮磷鉀含量預(yù)測(cè)的R2分別為0.961、0.954、0.958,RMSE分別為0.294%、0.262%、0.196%,實(shí)現(xiàn)了很好的建模效果。使用該模型對(duì)另2個(gè)品種西瓜進(jìn)行測(cè)試,R2超過(guò)0.899、RMSE小于0.498%,表明該模型具有很好的泛化性。該高光譜建模方法使用少量波長(zhǎng)光譜即實(shí)現(xiàn)了高精度檢測(cè),在精度和效率上達(dá)成了很好的平衡,為后續(xù)便攜式高光譜檢測(cè)裝備開發(fā)奠定了理論基礎(chǔ)。

    Abstract:

    Element content non-destructive testing technology can provide key real-time data for precise environmental regulation of plant growth and development. Taking watermelon seedlings as an example, a deep learning detection method based on graph feature fusion for nitrogen, phosphorus, and potassium content was proposed. Firstly, high-resolution hyperspectral images of watermelon seedling leaves were captured by using a hyperspectral image. The content of the three elements in the leaves was determined by using a continuous flow chemical analyzer. Then, the BOC-GF spectral preprocessing method and the RF algorithm were used to establish a prediction model. Based on the CARS and SPA algorithms, feature bands were preliminarily selected. Then, considering the number of bands and modeling accuracy, an optimal band evaluation method was designed to further reduce the number of bands to 3~4. Finally, the colour and texture features of the colour images segmented by using the U-Net network were extracted and used as inputs along with the spectral reflectance features to construct a prediction model for the three elemental contents based on the Self-Attention-BiLSTM network. The experimental results showed that the R2 values for predicting nitrogen, phosphorus, and potassium content were 0.961, 0.954, and 0.958, respectively, with corresponding RMSE values of 0.294%, 0.262%, and 0.196%. These results indicated a high level of modeling accuracy. Using this model to test two other varieties of watermelon, the R2 values exceeded 0.899 and the RMSE values were less than 0498%, indicating that the model had excellent generalization ability. This hyperspectral modeling method achieved high accuracy detection with a small number of spectral bands, striking a good balance between precision and efficiency. It laied a solid theoretical foundation for the development of portable hyperspectral detection equipment in the future.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

徐勝勇,劉政義,黃遠(yuǎn),曾雨,別之龍,董萬(wàn)靜.基于Self-Attention-BiLSTM網(wǎng)絡(luò)的西瓜種苗葉片氮磷鉀含量高光譜檢測(cè)方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2024,55(8):243-252. XU Shengyong, LIU Zhengyi, HUANG Yuan, ZENG Yu, BIE Zhilong, DONG Wanjing. Hyperspectral Non-destructive Detection of Nitrogen, Phosphorus and Potassium Content of Watermelon Seedling Leaves Based on Self-Attention-BiLSTM Network[J]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(8):243-252.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2023-11-22
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2024-08-10
  • 出版日期: