Integrating Drone Technology into an Innovative Agrometeorological Methodology for the Precise and Real-Time Estimation of Crop Water Requirements DOI Creative Commons
Stavros Alexandris, Emmanouil Psomiadis, Nikolaos Proutsos

et al.

Hydrology, Journal Year: 2021, Volume and Issue: 8(3), P. 131 - 131

Published: Sept. 1, 2021

Precision agriculture has been at the cutting edge of research during recent decade, aiming to reduce water consumption and ensure sustainability in agriculture. The proposed methodology was based on crop stress index (CWSI) applied Greece within ongoing project GreenWaterDrone. innovative approach combines real spatial data, such as infrared canopy temperature, air relative humidity, thermal image taken above field using an aerial micrometeorological station (AMMS) a (IR) camera installed unmanned vehicle (UAV). Following initial calibration phase, where ground (GMMS) crop, no equipment needed be maintained field. Aerial measurements were transferred time sophisticated databases applications over existing mobile networks for further processing estimation actual requirements specific level, dynamically alerting/informing local farmers/agronomists irrigation necessity additionally potential risks concerning their fields. supported services address farmers’, agricultural scientists’, stakeholders’ needs conform regional management sustainable policies. As preliminary results this study, we present indicative original illustrations data from applying assess UAV functionality while evaluate standardize all system processes.

Language: Английский

Combining Spectral and Texture Features of UAS-Based Multispectral Images for Maize Leaf Area Index Estimation DOI Creative Commons
Xuewei Zhang, Kefei Zhang,

Yaqin Sun

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(2), P. 331 - 331

Published: Jan. 11, 2022

The leaf area index (LAI) is of great significance for crop growth monitoring. Recently, unmanned aerial systems (UASs) have experienced rapid development and can provide critical data support LAI This study investigates the effects combining spectral texture features extracted from UAS multispectral imagery on maize estimation. Multispectral images in situ were collected test sites Tongshan, Xuzhou, Jiangsu Province, China. remote sensing are using vegetation indices (VIs) gray-level co-occurrence matrix (GLCM), respectively. Normalized (NDTIs), ratio (RTIs), difference (DTIs) calculated two GLCM-based textures to express influence different monitoring at same time. prescreened through correlation analysis. Different dimensionality reduction or feature selection methods, including stepwise (ST), principal component analysis (PCA), ST combined with PCA (ST_PCA), coupled vector regression (SVR), random forest (RF), multiple linear (MLR) build estimation models. results reveal that ST_PCA SVR has better performance, terms VIs + DTIs (R2 = 0.876, RMSE 0.239) NDTIs 0.877, 0.236). introduces potential demonstrates promising solution realize improving accuracy LAI.

Language: Английский

Citations

73
A Bibliometric Review of the Use of Unmanned Aerial Vehicles in Precision Agriculture and Precision Viticulture for Sensing Applications DOI Creative Commons
Abhaya Pal Singh, Amol Yerudkar, Valerio Mariani

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(7), P. 1604 - 1604

Published: March 27, 2022

This review focuses on the use of unmanned aerial vehicles (UAVs) in precision agriculture, and specifically, viticulture (PV), is intended to present a bibliometric analysis their developments field. To this aim, research papers published last 15 years presented based Scopus database. The shows that researchers from United States, China, Italy Spain lead agriculture through UAV applications. In terms employing UAVs PV, are fast extending work followed by finally States. Additionally, paper provides comprehensive study popular journals for academicians submit work, accessible funding organizations, nations, institutions, authors conducting utilizing agriculture. Finally, emphasizes necessity using PV as well future possibilities.

Language: Английский

Citations

51
Improving Wheat Yield Prediction Accuracy Using LSTM-RF Framework Based on UAV Thermal Infrared and Multispectral Imagery DOI Creative Commons

Yulin Shen,

Benoît Mercatoris, Zhen Cao

et al.

Agriculture, Journal Year: 2022, Volume and Issue: 12(6), P. 892 - 892

Published: June 20, 2022

Yield prediction is of great significance in agricultural production. Remote sensing technology based on unmanned aerial vehicles (UAVs) offers the capacity non-intrusive crop yield with low cost and high throughput. In this study, a winter wheat field experiment three levels irrigation (T1 = 240 mm, T2 190 T3 145 mm) was conducted Henan province. Multispectral vegetation indices (VIs) canopy water stress (CWSI) were obtained using an UAV equipped multispectral thermal infrared cameras. A framework combining long short-term memory neural network random forest (LSTM-RF) proposed for predicting VIs CWSI from multi-growth stages as predictors. Validation results showed that R2 0.61 RMSE value 878.98 kg/ha achieved grain LSTM. LSTM-RF model better compared to LSTM n 0.78 684.1 kg/ha, which equivalent 22% reduction RMSE. The considered both time-series characteristics growth process non-linear between remote data data, providing alternative accurate modern management.

Language: Английский

Citations

45
Retrieving SPAD Values of Summer Maize Using UAV Hyperspectral Data Based on Multiple Machine Learning Algorithm DOI Creative Commons

Bilige Sudu,

Guangzhi Rong,

Suri Guga

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(21), P. 5407 - 5407

Published: Oct. 28, 2022

Using unmanned aerial vehicle (UAV) hyperspectral images to accurately estimate the chlorophyll content of summer maize is great significance for crop growth monitoring, fertilizer management, and development precision agriculture. Hyperspectral imaging data, analytical spectral devices (ASD) SPAD values in different key periods were obtained under conditions a micro-spray strip drip irrigation water supply. The data preprocessed by transformation methods. Then, several algorithms including Findpeaks (FD), competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), CARS_SPA used extract sensitive characteristic bands related from image UAV. Subsequently, four machine learning regression models partial least squares (PLSR), random forest (RF), extreme gradient boosting (XGBoost), deep neural network (DNN) establish value estimation models. results showed that correlation coefficient between ASD UAV was greater than 0.96 indicating could be information. selected slightly different. effectively characteristics. This not only greatly reduced number characteristics but also improved multiple collinearity problem. low frequency information SSR significantly improve ability maize. In accuracy verification PLSR, RF, XGBoost, DNN inversion model based on CARS_SPA, determination coefficients (R2) 0.81, 0.42, 0.65, 0.82, respectively. better other Compared with high-frequency information, low-frequency (DNN CARS_SPA) had strong estimating canopy. study provides reference technical support rapid non-destructive testing

Language: Английский

Citations

43
UAV multispectral images for accurate estimation of the maize LAI considering the effect of soil background DOI Creative Commons
Shuaibing Liu, Xiuliang Jin, Yi Bai

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 121, P. 103383 - 103383

Published: June 8, 2023

The high proportion of soil background pixels in UAV remote sensing images is an important reason for the uncertainty high-precision leaf area index (LAI) estimation at early growth stages crops. Although traditional method removing from based on canopy coverage (CC) eliminates pure pixels, it can cause spectral saturation and therefore affect accuracy LAI estimation. In this study, a new called reduced contribution (CS) was constructed to improve This be improved by introducing quantitative account information, which used correct calculation vegetation indices eliminate interference maize A six-rotor equipped with multispectral camera collect field image data. Experimental plots different breeding varieties were laid out carefully evaluate model using collected stages. performance four models, light gradient boosting machine, gradient-boosting decision tree, random forest regression extreme boosting, evaluated. CS-based approach significantly estimation, reducing rRMSE 1.89% single growing season compared method. On average, all decreased 3.5%, demonstrating its effectiveness improving accuracy. Randomness error measured Moran's I metrics showed that GBDT (gradient-boosting trees) CS less spatial aggregation. These results effectively reduce influence direct removal image.

Language: Английский

Citations

41
Combining Spectral and Textural Information from UAV RGB Images for Leaf Area Index Monitoring in Kiwifruit Orchard DOI Creative Commons
Youming Zhang, Na Ta, Song Guo

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(5), P. 1063 - 1063

Published: Feb. 22, 2022

The use of a fast and accurate unmanned aerial vehicle (UAV) digital camera platform to estimate leaf area index (LAI) kiwifruit orchard is great significance for growth, yield estimation, field management. LAI, as an ideal parameter estimating vegetation plays significant role in reflecting crop physiological process ecosystem function. At present, LAI estimation mainly focuses on winter wheat, corn, soybean, other food crops; addition, forest research also predominant, but there are few studies the application orchards such kiwifruit. Concerning this study, high-resolution UAV images three growth stages were acquired from May July 2021. extracted significantly correlated spectral textural parameters used construct univariate multivariate regression models with measured corresponding stages. optimal model was selected mapping by comparing stepwise (SWR) random (RFR). Results showed combining texture features superior that only based indices prediction accuracy modeling set, R2 0.947 0.765, RMSE 0.048 0.102, nRMSE 7.99% 16.81%, respectively. Moreover, RFR (R2 = 0.972, 0.035, 5.80%) exhibited best followed SWR 16.81%) linear 0.736, 0.108, 17.84%). It concluded method combined can provide effective monitoring. expected scientific guidance practical methods management low-cost remote sensing technology realize large high-quality monitoring thus providing theoretical basis investigation.

Language: Английский

Citations

40
Cotton Verticillium wilt monitoring based on UAV multispectral-visible multi-source feature fusion DOI
Rui Ma, Nannan Zhang, Xiao Zhang

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 217, P. 108628 - 108628

Published: Jan. 21, 2024

Language: Английский

Citations

14
Dos and Don'ts of using drone technology in the crop fields DOI
Jamileh Aliloo, Enayat Abbasi, Esmail Karamidehkordi

et al.

Technology in Society, Journal Year: 2024, Volume and Issue: 76, P. 102456 - 102456

Published: Jan. 2, 2024

Language: Английский

Citations

11
UAV image acquisition and processing for high‐throughput phenotyping in agricultural research and breeding programs DOI Creative Commons
Ocident Bongomin, Jimmy Lamo,

Joshua Mugeziaubwa Guina

et al.

The Plant Phenome Journal, Journal Year: 2024, Volume and Issue: 7(1)

Published: Feb. 19, 2024

Abstract We are in a race against time to combat climate change and increase food production by 70% feed the ever‐growing world population, which is expected double 2050. Agricultural research plays vital role improving crops livestock through breeding programs good agricultural practices, enabling sustainable agriculture systems. While advanced molecular technologies have been widely adopted, phenotyping as an essential aspect of has seen little development most African institutions remains traditional method. However, concept high‐throughput (HTP) gaining momentum, particularly context unmanned aerial vehicle (UAV)‐based phenotyping. Although into UAV‐based still limited, this paper aimed provide comprehensive overview understanding use UAV platforms image analytics for HTP identify key challenges opportunities area. The discusses field concepts, classification specifications, cases phenotyping, imaging systems processing methods. more required optimize UAVs’ performance data acquisition, limited studies focused on effect operational parameters acquisition.

Language: Английский

Citations

11
Towards efficient irrigation management at field scale using new technologies: A systematic literature review DOI Creative Commons

Afaf Bounajra,

Kamal El Guemmat, Khalifa Mansouri

et al.

Agricultural Water Management, Journal Year: 2024, Volume and Issue: 295, P. 108758 - 108758

Published: March 5, 2024

Life on earth is linked to water resources. Recently, alarm bells have been ringing in global organizations raise awareness of the importance rational use resources, which are becoming an increasingly scarce commodity. The majority world's freshwater used for agricultural irrigation, hence there a need adopt intelligent irrigation strategy that will lead sustainable management. To reap full benefits, must be accompanied by good understanding field characteristics. Several studies benefited from improvement new technologies scheduling, but taking only soil properties as basis research, and our knowledge no systematic literature review study date aims at scheduling into consideration characteristics crop efficient This article explore Internet Things Artificial Intelligence one hand monitoring predicting coefficients control evapotranspiration process responsible losses, namely reference coefficient ETo Kc, other the: physical, chemical, biological hydrological specific field, affect therefore yield. Following methodology led us refined selection 55 journal articles further analysis. We identified profitability closely right strategies adopted plot, these can defined after field's were able discuss through primary enabled develop model brings together different approaches farm management identify gaps limitations scale, thus pave way research.

Language: Английский

Citations

10