Quantifying Hail Damage in Crops Using Sentinel-2 Imagery

Ha, Thuan; Shen, Yanben; Duddu, Hema; Johnson, Eric N.; Shirtliffe, Steven J.

doi:10.3390/rs14040951

Cited by 15 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, this method cannot analyze several other crops like wheat, soybeans, and sugarcane. Ha et al (2022) established crop losses due to hail disasters with the sentimental-2 imagery technique. This study examined canola, wheat, and lentil crops in the Canadian region for hail damage.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

Kumar,

Mahapatra

2024

World Water Policy

View full text Add to dashboard Cite

Crop yield prediction has gained major potential for global food production. Predicting crop yields based on specific parameters like soil, environment, crop, and water has been an interesting research topic in recent decades. To accurately predict crop yields, measuring the severities of natural calamities including water level is mainly required. However, the existing studies failed to predict crop yields accurately because of various issues like overfitting problems, difficulty in training, inability to handle large data, and reduced learning capability. Thus, the proposed study develops an efficient mechanism for accurately predicting crop yields by analyzing several natural calamities. Here, the input samples are initially pre‐processed to remove unwanted noises using data normalization and standardization. To enhance the performance of crop yield prediction, natural calamities are computed by using an Extreme Gradient Boosting (XGBoost) model based on parameters like the Palmer Drought Severity Index (PDSI), Severe Hail Index (SHI), and Storm Severity Index (SSI). Also, the hyperparameters of XGBoost model are tuned by utilizing Sheep Flock Optimization Algorithm (SFOA). Finally, the crop yield is predicted by proposing a new one‐dimensional convolutional gated recurrent unit neural network (1D‐CGRU). The proposed classifier predicts the crop yields with reduced error rates like mean square error (MSE) of 0.4363, root mean square error (RMSE) of 0.1904, normalized root mean squared error (NRMSE) of 0.00101, mean absolute error (MAE) of 0.2437, and R‐squared (R2) of .2756. Also, the significant findings of the proposed study positively indicate that this study can be applicable to real‐time agricultural practices and is highly suitable for water quality predictions. Also, it can assist farmers and farming businesses in predicting the yield of crops in a specific season when to harvest and crop a plant for attaining improved crop yields.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Ha et al (2022) established crop losses due to hail disasters with the sentimental‐2 imagery technique. This study examined canola, wheat, and lentil crops in the Canadian region for hail damage.…”

Section: Related Workmentioning

confidence: 99%

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

Kumar,

Mahapatra

2024

World Water Policy

View full text Add to dashboard Cite

show abstract

“…Additionally, given the labor‐intensive task of assessing crop damage on the ground, other areas of future research should include the study of technologies to help rapidly and efficiently assess the damage in the crop—for example, crop models, satellite imagery, remote sensing (e.g., normalized difference vegetation index, NDVI), unmanned aerial vehicles, radar‐derived information for estimating crop stands, defoliation levels, and yield losses in affected fields. Although some of these efforts have been established recently (Bell & Molthan, 2016; Bell et al., 2020; Erda et al., 2012; Ha et al., 2022; Zhou et al., 2016), major limitations remain. These include reliable data sources, time for model development, model calibrations, and model validations, which at first are labor intensive and have other limitations such as technology costs, cloud coverage, surface variability (e.g., soil moisture, crop maturity, weeds presence), and dissecting crop damage from hail compared to other potential causes (e.g., insect defoliation).…”

Section: Hail/defoliation Damagementioning

confidence: 99%

Severe storm damage and short‐term weather stresses on corn: A review

Lindsey,

Ortez,

Thomison

et al. 2024

Crop Science

View full text Add to dashboard Cite

Adverse weather conditions from acute events (e.g., storms causing lodging, flooding, or hail) or short‐duration weather patterns (i.e., periods of cold events; extended waterlogged field conditions) can result in yield losses, though management practices may play key roles in aiding with crop recovery or avoidance of these stress events. This review summarizes current knowledge (with emphasis placed on the US Midwest) related to corn response to short‐term weather stresses of (i) cold temperature, (ii) excess water, (iii) hail/defoliation damage, and (iv) wind damage. Each section presents summaries of how corn growth and yield are affected, provides context into past events experienced, identifies agronomic or production recommendations to correct or alleviate the stress condition, and proposes areas where future research is needed. This review also highlights challenges associated with controlled simulation work on these stressors, and also identifies key areas to expand future research efforts. In general, yield losses associated with strong storms and short‐term weather events often ranged from 5% to 35%, but extreme cases could result in up to 80%–100% yield loss. Much of the literature on these topics was published prior to 1995, though it still forms the basis for modern agronomic guidance, which is problematic given the changes in agriculture in the last 20 years in management practices, available genetics and technologies, and changing environmental conditions. Revisiting these foundational studies and expanding them to examine current and future weather conditions are critical for better informing agronomic recommendations, for devising mitigation strategies, and for determining accurate yield loss expectations following these stresses.

show abstract

“…'Canola'), and lentil (Lens culinaris Medik. ; Ha et al, 2022). Crop producers surveyed indicated that they perceive wheat is more sensitive than corn (Zea mays L.) to hail damage due to its smaller seed and head size (Childs et al, 2020).…”

mentioning

confidence: 99%

Impact of simulated hail damage at different growth stages and canopy positions on rainfed and irrigated winter wheat

et al. 2023

View full text Add to dashboard Cite

Producers and crop insurance providers will benefit from an accurate assessment of yield reduction after hailstorms that considers crop management, weather, growth stage, and impacted part of crop (hail affected canopy position). But, limited information is available. The main objectives of this study were to quantify wheat (Triticum aestivum L.) yield losses associated with simulated hail damage timing and canopy position. The study was conducted in two locations (Garden City [irrigated], and Manhattan [rainfed]) in Kansas, from 2018 to 2020 and 2016 to 2018, respectively.Treatments were an incomplete factorial combination of stem bending at seven flowering stages, above or below the flag leaf and a nontreated control. Results of the study indicated 11%-22% wheat yield reduction due to simulated hail damage above the flag leaf and 32%-52% due to hail impact below the flag leaf under irrigated conditions. Within the high-yielding rainfed environment, hail damage caused up to 20% yield reduction compared with the control. In rainfed and low-yielding environments, the impact of hail damage was mainly dependent on the growth stage of wheat at hail occurrence. Hail damage at Feekes 11.2-11.4 stages decreased yield by 20%-50% from the rainfed control. Hail damage at Feekes 10.0-10.5.4 decreased yield by 50%-70% from the rainfed control. We provide empirical evidence that indicates hail damage on wheat is dependent on the interaction effect of in-season crop water management, weather, canopy position and crop growth stage, and estimates of yield loss due to hail should consider these factors. INTRODUCTIONHail damage reduces crop yield by bending and breaking the stems, causing crop lodging, defoliation, direct grain loss, and plant death with hail stones that are >5 mm in diameter (

show abstract

Quantifying Hail Damage in Crops Using Sentinel-2 Imagery

Cited by 15 publications

References 38 publications

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

Severe storm damage and short‐term weather stresses on corn: A review

Impact of simulated hail damage at different growth stages and canopy positions on rainfed and irrigated winter wheat

Contact Info

Product

Resources

About