Recent studies have explored various methods for automatic sugarcane yield estimation using Unmanned Aerial Vehicles (UAVs), focusing on different aspects of the process.
One study used a machine learning approach based on UAV-LiDAR data, where Random Forest Regression (RFR) showed the best performance in estimating sugarcane aboveground fresh weight with high accuracy (R<sup>2</sup> = 0.96 and RMSE of 1.27 kg/m<sup>2</sup>) (Xu et al., 2020). Another study integrated an RGB-based vegetation index, crop surface models, and object-based image analysis for sugarcane yield estimation with a minimal field dataset ([SumeshK. et al.]). Additionally, research has been conducted to compare qualitative and quantitative UAV data with field and satellite data for monitoring sugarcane ([Souza]), while another study used UAV photos and ground data through simple regression and correlation analysis to predict yields (Prommahakul et al., 2020).
Montes et al. (2021) emphasized the estimation of different yield variables through aerial photos and photogrammetric methods, calibrated against measured field data (Montes et al., 2021). For improving the estimation accuracy, Liangsheng Shi et al. (2018) assimilated UAV-derived Leaf Area Index (LAI) and ground-measured Soil Water Content (SWC) data into a crop model, using the ensemble Kalman filter method, which showed satisfactory results (Shi et al., 2018).
High-resolution UAS images have also been employed to generate crop surface models and estimate sugarcane height, serving as a yield indicator (de Souza et al., 2017). Moreover, drones have been used to monitor meteorological disasters impacting sugarcane crops, finding that long-term flooding can lead to crop failures whereas the damage from gales is minimal (Ma et al., 2018).
In weed identification within sugarcane fields, Artificial Neural Networks proved to be the best classifier, achieving an overall accuracy of 91.67% in images taken by UAV ([Yano et al.]). Acknowledging the potential of UAVs towards sustainable agriculture, the review by Hafsal focused on UAV and Soil Moisture Content estimation synergy ([Hafsal]).
For optimizing agricultural activities and maximizing productivity, computer vision techniques, digital image processing, and machine learning algorithms have been found useful in automated processes specific to the sugar industry (Dhariwal & Sharma, 2022). UAVs play a central role in sustainable and efficient farming practices, not just in automatic yield estimation but also in monitoring plant growth cycles (Yaqot & Menezes, 2021).
Lastly, merging multispectral images with machine learning algorithms has developed a non-invasive predictive framework mapping canopy reflectance to quality indicators like °Brix and Purity, with at least 80% adequacy for modeling in sugarcane (Barbosa Júnior et al., 2023). These studies show how technology can enhance yield estimation, offering accurate, rapid, and less labor-intensive alternatives to traditional methods.
- Estimation of Sugarcane Yield Using a Machine Learning Approach Based on UAV-LiDAR DataJing-Xian XuJun MaYa-Nan TangWei-Xiong WuJingbang ShaoWanben WuS. WeiYi-Fei LiuYuan-Chen WangHai-Qiang GuoCited byLanding PagePDF Link
- Integration of RGB-based vegetation index, crop surface model and object-based image analysis approach for sugarcane yield estimation using unmanned aerial vehicleC. SumeshK.S. NinsawatJ. Som-ardCited byLanding PagePDF Link
- Retrieval of field-level information of sugarcane using unmanned aerial vehicle (UAV) data under different approaches = Aquisição de informações em nível de campo da cana-de-açúcar utilizando dados de um veículo aéreo não tripulado (VANT) sob diferentes metodologiasC. SouzaCited byLanding PagePDF Link
- Sugarcane Land Change Pattern and Yield Prediction Using Landsat Imagery and Unmanned Aerial Vehicle PhotosKomkrid PrommahakulNuttapong PheunsongkhamJ. Som-ardWorawit JitsukkCited byLanding PagePDF Link
- Estimación de rendimiento en el cultivo de caña de azúcar (Saccharum officinarum) a partir de fotogrametría con vehículos aéreos no tripulados (VANT)B. MontesC. HenríquezT. R. RodríguezKenneth Largaespada ZelayaCited byLanding PagePDF Link
- Estimation of Sugarcane Yield by Assimilating UAV and Ground Measurements Via Ensemble Kalman FilterLiangsheng ShiShun HuY. ZhaCited byLanding PagePDF Link
- Height estimation of sugarcane using an unmanned aerial system (UAS) based on structure from motion (SfM) point cloudsC. H. W. de SouzaR. LamparelliJ. RochaP. G. MagalhãesCited byLanding PagePDF Link
- Experiment of Meteorological Disaster Monitoring on Unmanned Aerial VehicleR. MaXiaozheng LiMingwei SunZhaomin KuangCited byLanding PagePDF Link
- CHOOSING CLASSIFIER FOR WEED IDENTIFICATION IN SUGARCANE FIELDS THROUGH IMAGES TAKEN BY UAVInácio YanoW. E. SantiagoJ. R. AlvesL. ToledoMoreira MotaB. TeruelCited byLanding PagePDF Link
- Precision Agriculture with Unmanned Aerial Vehicles for SMC estimations – Towards a more Sustainable AgricultureLeif Peder HafsalCited byLanding PagePDF Link
- An investigation on the best-fit models for sugarcane biomass estimation by linear mixed-effect modelling on unmanned aerial vehicle-based multispectral images: A case study of AustraliaS. AkbarianChengyuan XuWeijin WangStephen GinnsSamsung LimCited byLanding PagePDF Link
- Remote Sensing Applications in Sugarcane Cultivation: A ReviewJ. Som-ardC. AtzbergerE. Izquierdo-VerdiguierF. VuoloMarkus ImmitzerCited byLanding PagePDF Link
- UAV‐based NDVI estimation of sugarbeet yield and quality under varied nitrogen and water ratesO. WalshE. NambiS. ShafianDileepa M. JayawardenaE. AnsahRitika LamichhaneJordan R. McClintick‐ChessCited byLanding PagePDF Link
- Aerial Images were used to Detect Curved-Crop Rows and Failures in Sugarcane ProductionSumit DhariwalAvani SharmaCited byLanding PagePDF Link
- Unmanned Aerial Vehicle (UAV) in Precision Agriculture: Business Information Technology Towards Farming as a ServiceMohammed YaqotB. MenezesCited byLanding PagePDF Link
- UAV imagery data and machine learning: A driving merger for predictive analysis of qualitative yield in sugarcaneMarcelo Rodrigues Barbosa JúniorB. R. D. A. MoreiraRomário Porto de OliveiraL. ShiratsuchiR. P. da SilvaCited byLanding PagePDF Link
- RISK ANALYSIS FOR APPLE ORCHARD SURVEY AND MONITORING USING UAVL. LitavnieceS. KodorsJuta DeksneG. LācisImants ZaremboAntons PacejsCited byLanding PagePDF Link
- ANALYSIS ON THE EFFECT OF SPATIAL AND SPECTRAL RESOLUTION OF DIFFERENT REMOTE SENSING DATA IN SUGARCANE CROP YIELD STUDYS. AkbarianC.-Y. XuSamsung LimCited byLanding PagePDF Link
- Scoring Cercospora Leaf Spot on Sugar Beet: Comparison of UGV and UAV Phenotyping SystemsS. JayAlexis ComarR. BenícioJ. BeauvoisDan DutartreG. DaubigeWenjuan LiJ. LabrosseSamuel ThomasN. HenryM. WeissF. BaretCited byLanding PagePDF Link
- Fresh Yield Estimation of Spring Tea via Spectral Differences in UAV Hyperspectral Images from Unpicked and Picked CanopiesZongtai HeKaihua WuFumin WangLisong JinRongxu ZhangShoupeng TianWeizhi WuYadong HeRan HuangLin YuanYao ZhangCited byLanding PagePDF Link
- Remote Sensing Identification and Rapid Yield Estimation of Pitaya Plants in Different Karst Mountainous Complex HabitatsZhongfa ZhouRuiwen PengRuoshuang LiYiqiu LiDenghong HuangMeng ZhuCited byLanding PagePDF Link
- A Review on Unmanned Aerial Vehicle Remote Sensing: Platforms, Sensors, Data Processing Methods, and ApplicationsZhengxin ZhangLixue ZhuCited byLanding PagePDF Link
- Estimating Black Oat Biomass Using Digital Surface Models and a Vegetation Index Derived from RGB-Based Aerial ImagesL. R. TrevisanL. BrichiT. M. GomesF. RossiCited byLanding PagePDF Link
- Diagnosis of the Rice lodging for the UAV Image using Vision TransformerHyunjung MyungSeo-jeong KimKangin ChoiDonghoon KimGwanghyeong LeeHyung-geun AhnSunghwan JeongByoungjun KimCited byLanding PagePDF Link
- Maize Nitrogen Grading Estimation Method Based on UAV Images and an Improved Shufflenet NetworkWeizhong SunBohan FuZhao ZhangCited byLanding PagePDF Link