Estimation of Bale Grazing and Sacrificed Pasture Biomass through the Integration of Sentinel Satellite Images and Machine Learning Techniques

Vahidi, Milad; Shafian, Sanaz; Thomas, Summer; Maguire, Rory

doi:10.3390/rs15205014

Cited by 3 publications

(2 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In numerous studies, researchers have employed meta-heuristic algorithms to identify the most effective spectral bands, while machine learning architectures have been utilized to categorize HS images [5,[42][43][44][45]. Ghadi et al [5] developed an innovative migration-based particle swarm optimization (MBPSO) tailored for the optimal selection of spectral bands.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization

Shoeibi,

Nevisi,

Salehi

et al. 2024

CMC

View full text Add to dashboard Cite

Hyperspectral (HS) image classification plays a crucial role in numerous areas including remote sensing (RS), agriculture, and the monitoring of the environment. Optimal band selection in HS images is crucial for improving the efficiency and accuracy of image classification. This process involves selecting the most informative spectral bands, which leads to a reduction in data volume. Focusing on these key bands also enhances the accuracy of classification algorithms, as redundant or irrelevant bands, which can introduce noise and lower model performance, are excluded. In this paper, we propose an approach for HS image classification using deep Q learning (DQL) and a novel multi-objective binary grey wolf optimizer (MOBGWO). We investigate the MOBGWO for optimal band selection to further enhance the accuracy of HS image classification. In the suggested MOBGWO, a new sigmoid function is introduced as a transfer function to modify the wolves' position. The primary objective of this classification is to reduce the number of bands while maximizing classification accuracy. To evaluate the effectiveness of our approach, we conducted experiments on publicly available HS image datasets, including Pavia University, Washington Mall, and Indian Pines datasets. We compared the performance of our proposed method with several state-of-the-art deep learning (DL) and machine learning (ML) algorithms, including long short-term memory (LSTM), deep neural network (DNN), recurrent neural network (RNN), support vector machine (SVM), and random forest (RF). Our experimental results demonstrate that the Hybrid MOBGWO-DQL significantly improves classification accuracy compared to traditional optimization and DL techniques. MOBGWO-DQL shows greater accuracy in classifying most categories in both datasets used. For the Indian Pine dataset, the MOBGWO-DQL architecture achieved a kappa coefficient (KC) of 97.68% and an overall accuracy (OA) of 94.32%. This was accompanied by the lowest root mean square error (RMSE) of 0.94, indicating very precise predictions with minimal error. In the case of the Pavia University dataset, the MOBGWO-DQL model demonstrated outstanding performance with the highest KC of 98.72% and an impressive OA of 96.01%. It also recorded the lowest RMSE at 0.63, reinforcing its accuracy in predictions. The results clearly demonstrate that the proposed MOBGWO-DQL architecture not only reaches a highly accurate model more quickly but also maintains superior performance throughout the training process.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization

Shoeibi,

Nevisi,

Salehi

et al. 2024

CMC

View full text Add to dashboard Cite

show abstract

“…Moreover, Milad et al applied an integration Sentinel product (10 m Sentinel-1 and Sentinel-2 images) and different learning tools to estimate tall fescue pasture biomass over different paddock types. The developed model could estimate pasture biomass with an accuracy of 0.83 [7].…”

Section: Introductionmentioning

confidence: 99%

Pasture Biomass Estimation Using Ultra-High-Resolution RGB UAVs Images and Deep Learning

Vahidi,

Shafian,

Thomas

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

The continuous assessment of grassland biomass during the growth season plays a vital role in making informed, location-specific management choices. The implementation of precision agriculture techniques can facilitate and enhance these decision-making processes. Nonetheless, precision agriculture depends on the availability of prompt and precise data pertaining to plant characteristics, necessitating both high spatial and temporal resolutions. Utilizing structural and spectral attributes extracted from low-cost sensors on unmanned aerial vehicles (UAVs) presents a promising non-invasive method to evaluate plant traits, including above-ground biomass and plant height. Therefore, the main objective was to develop an artificial neural network capable of estimating pasture biomass by using UAV RGB images and the canopy height models (CHM) during the growing season over three common types of paddocks: Rest, bale grazing, and sacrifice. Subsequently, this study first explored the variation of structural and color-related features derived from statistics of CHM and RGB image values under different levels of plant growth. Then, an ANN model was trained for accurate biomass volume estimation based on a rigorous assessment employing statistical criteria and ground observations. The model demonstrated a high level of precision, yielding a coefficient of determination (R2) of 0.94 and a root mean square error (RMSE) of 62 (g/m2). The evaluation underscores the critical role of ultra-high-resolution photogrammetric CHMs and red, green, and blue (RGB) values in capturing meaningful variations and enhancing the model’s accuracy across diverse paddock types, including bale grazing, rest, and sacrifice paddocks. Furthermore, the model’s sensitivity to areas with minimal or virtually absent biomass during the plant growth period is visually demonstrated in the generated maps. Notably, it effectively discerned low-biomass regions in bale grazing paddocks and areas with reduced biomass impact in sacrifice paddocks compared to other types. These findings highlight the model’s versatility in estimating biomass across a range of scenarios, making it well suited for deployment across various paddock types and environmental conditions.

show abstract

Aboveground biomass estimation in conifer and deciduous forests with the use of a combined approach

Lovynska,

Sytnyk,

Stankevich

et al. 2024

Biosys. divers.

View full text Add to dashboard Cite

The complex action of environmental factors often triggers the biomass formation in forest plantations, which is crucial for carbon balance and environmental monitoring, especially in the context of climate change. In this article, we present data on the aboveground biomass accumulation for black locust and common pine (Pinus sylvestris and Robinia pseudoacacia) as the two most common forest-forming species in the steppe zone. For this purpose, we propose a reliable approach to monitoring of aboveground forest biomass with combining Sentinel-2 multispectral imaging techniques (with L-band) and biometric processing data from coniferous and deciduous stands obtained from field surveys. We represent the results of field surveys with established indicators of aboveground biomass of forest plantations in the field experiment, which averaged 159.9 ± 9.0 t/ha in the studied region. The biometric indexes obtained from the field experiments were used to develop models for predicting biomass using the remote method. Based on the processing of satellite image data, forest vegetation indices were analysed, among which the NDVI (normalized difference vegetation index) was the best predictor to assess biomass. The multiple regression method was found to be the best for predicting and mapping the aboveground biomass in P. sylvestris and R. pseudoacacia within the studied area (RMSE – 23.46 t/ha). Based on the results obtained, we created a map of the aboveground biomass distribution in black locust and common pine stands within the studied region. We established reliable correlations between biometric parameters (mean diameter at breast height, mean height) and aboveground biomass of stands with indicators of spectral bands in satellite images. This enables us to use the constructed models to estimate the overall productivity of coniferous and deciduous forest stands for large areas.

show abstract

Estimation of Bale Grazing and Sacrificed Pasture Biomass through the Integration of Sentinel Satellite Images and Machine Learning Techniques

Cited by 3 publications

References 67 publications

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization

Pasture Biomass Estimation Using Ultra-High-Resolution RGB UAVs Images and Deep Learning

Aboveground biomass estimation in conifer and deciduous forests with the use of a combined approach

Contact Info

Product

Resources

About