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

XU Shengyong, LIU Zhengyi, HUANG Yuan, ZENG Yu, BIE Zhilong, DONG Wanjing

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.

 

Keywords: watermelon seedling leaves;element content;non-destructive testing;self-attention mechnism;BiLSTM;Hyperspectral

 

Download Full Text:

PDF


References


NOEL M, MAR A, EL A M, et al. Analysis of vegetation indices to determine nitrogen application and yield prediction in maize (Zea mays L. ) from a standard LAV service[J]. Remote Sensing, 2018, 10(3) : 368 -378.

ZHA H, MIAO Y, WANG T, et al. Improving unmanned aerial vehicle remote sensing-based rice nitrogen nutrition index prediction with machine learning Г J ]. Remote Sensing, 2020, 12(2) ; 215 -221.

YE X, ABE S, ZHANG S. Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging [j]. Precision Agriculture, 2020, 21(1); 198 -225.

GAO J, MENG B, LIANG T, et al. Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China [ J ]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 147: 104 - 117.

XU S, XU X, BLACKER C, et al. Estimation of leaf nitrogen content in rice using vegetation indices and feature variable optimization with information fusion of multiple-sensor images from UAV[J]. Remote Sens. , 2023, 15(3) : 1 -24.

YANG Xin, YUAN Ziran, YE Yin, et al. Inversion of total nitrogen content of winter wheat based on UAV hyperspectral remote sensing [J]. Spectroscopy and Spectral Analysis, 2022, 42( 10) ; 3269 -3274. (in Chinese)

FAN Yiguang, FENG Haikuan, LIU Yang, et al. Estimation of potato plant nitrogen content based on canopy spectral characteristics and plant height [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(6) : 202 -208. ( in Chinese)

WANG Fan, CHEN Longyue, DUAN Dandan, et al. Hyperspectral monitoring of total nitrogen content in fresh tea leaves by wavelet analysis [J] . Spectroscopy and Spectral Analysis, 2022, 42( 10) ; 3235 -3242. (in Chinese)

XU Tongyu, JIN Zhongyu, GUO Zhonghui, et al. Simultaneous inversion method of nitrogen and phosphorus contents in rice leaves using CARS—RUN —ELM algorithm J . Transactions of the CSAE, 2022, 38( 10) ; 148 - 155. (in Chinese)

LU J, YANG T, SU X, et al. Monitoring leaf potassium content using hyperspectral vegetation indices in rice leaves [ J ]. Precision Agriculture, 2020, 21(2) ; 324 -348.

MEGAN A, JOE M, MATTHEW C, et al. Prediction of potassium in peach leaves using hyperspectral imaging and multivariate analysis [j]. AgriEngineering, 2022, 4: 400 -413.

ANNA S, PIOTR B, JOANNA P, et al. Identification of plant leaf phosphorus content at different growth stages based on hyperspectral reflectance [ J ]. BMC Plant Biology, 2021 , 21(28) ;1 - 17.

OSCO L P, RAMOS A, PEREIRA D R, et al. Predicting canopy nitrogen content in citrus-trees using random forest algorithm associated to spectral vegetation indices from UAV-imagery[ J]. Remote Sensing, 2019, 11(24) : 2925 -2931.

LI Pengcheng, LIU Han, ZHAO Longlian, et al. Key parameters for maize leaf moisture measurement using NIR camera with filters based on hyperspectral data[J], Spectroscopy and Spectral Analysis, 2021 , 41 ( 10) : 3184 -3188. (in Chinese)

ABULAITI Y, SAWUT M, MAIMAITIAILI B, et al. A possible fractional order derivative and optimized spectral indices for assessing total nitrogen content in cotton [J ]. Computers and Electronics in Agriculture, 2020, 171; 1052 - 1075.

WANG Yujie, GE Jina, LU Qingli, et al. NIR hyperspectral imaging coupled with chemometrics for nondestructive assessment of phosphorus and potassium contents in tea leaves [j]. Infrared Physics & Technology, 2020, 108:1 -9.

WANG Jinxing, LIU Xuemei, LIU Shuangxi, et al. Prediction of nitrogen content in apple leaves in each growth period based on combined color characteristics[ J]. Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52( 10) : 272 - 281. (in Chinese)

XIONG Juntao, DAI Senxin, OU Jionghong, et al. Leaf deficiency symptoms detection method of soybean based on deep learning [J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(1): 195 -202. (in Chinese)

ZHANG Yu, TIAN Haiqing, LI Zhe, et al. Nitrogen nutrition monitoring of beet canopy based on digital camera image[ J ]. Transactions of the CSAE, 2018, 34( 1 ) : 157 — 163. (in Chinese)

HECTOR G M, ROBERTO A H, ABDUL К G, et al. Corn grain yield estimation from vegetation indices, canopy cover, plant density, and a neural network using multispectral and RGB images acquired with unmanned aerial vehicles[J]. Agriculture, 2020, 10(7) ; 96 - 108.

SIIENG Ren, CHENG Wu, LI Huanhuan, et al. Model development for soluble solids and lycopene contents of cherry tomato at different temperatures using near-infrared spectroscopy [ J ] . Postharvest Biology and Technology, 2019, 156; 1 -9.

CHEN Shaomin, HU Tiantian, LUO Lihua, et al. Prediction of nitrogen, phosphorus, and potassium contents in apple tree leaves based on in-situ canopy hyperspectral reflectance using stacked ensemble extreme learning machine model[ J]. Journal of Soil Science and Plant Nutrition, 2022, 22( 10) :10 -24.


Refbacks

  • There are currently no refbacks.