Land-Cover Mapping of Agricultural Areas Using Machine Learning in Google Earth Engine

Hastings, Florencia; Fuentes, Ignacio; Perez‐Bidegain, Mario; Navas, Rafael; Gorgoglione, Angela

doi:10.1007/978-3-030-58811-3_52

Cited by 7 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average annual temperature and total precipitation during the period 1961-1990 are 17.5 °C and 1100 mm, respectively (25) . Between 1990 and 2018, a remarkable change in land use was registered in the San Salvador basin (Table 1 and Figure 2) (20) : cropland increased from 953 to 1,495 km 2 (57%), grassland decreased from 1,358 to 749 km 2 (45%), and production forest increased from 12 to 78 km 2 (570%). Land management also changed: in 1990, cropping with grazing combined with livestock and till practices prevailed, while in 2018, continuous cropping, no-till, and transgenic crops prevailed (26) .…”

Section: Study Areamentioning

confidence: 99%

“…This study considered the San Salvador watershed, an agricultural basin in Uruguay. This basin is representative of the agricultural expansion process of the country (20) and now has the potential to intensify its production through supplementary irrigation (21)(22) . The irrigation development changes land use and management and affects the water quality and quantity of the San Salvador River.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impacts of irrigation development on water quality in the San Salvador watershed (Part 1)

Hastings,

Pérez-Bidegain,

Navas

et al. 2024

Agrocienc Urug

View full text Add to dashboard Cite

The development of irrigation involves a change in land use and management and has implications for water quality and quantity. It is critical to design conservation practices and best management practices consistent with sustainable agricultural intensification. The objective of this work was to understand and characterize key processes affecting hydrology, nutrient export and transport, and quantify impacts in the San Salvador watershed. For such purpose, the Soil & Water Assessment Tool (SWAT) was implemented, calibrated for water quantity, and water quality was adjusted using soft calibration techniques. The model reproduces water quantity and nutrient balance, and aids in characterizing the nutrient delivery and transport in the watershed. The magnitude of runoff affects the balance of nutrients. In high flows, diffuse sources are more prevalent, while in low flows, point sources and direct livestock manure to the river are more significant. The main outcomes of this work contribute to the design of strategies to achieve sustainable agricultural intensification. It also describes a new modeling tool freely available that could be used in further studies.

show abstract

Section: Study Areamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Impacts of irrigation development on water quality in the San Salvador watershed (Part 1)

Hastings,

Pérez-Bidegain,

Navas

et al. 2024

Agrocienc Urug

View full text Add to dashboard Cite

show abstract

“…The San Salvador River basin belongs to a major agricultural area in the Southwest region of Uruguay characterised by a smooth hilled landscape under a humid subtropical climate and with an average precipitation of 1100 mm/year. Since 1990, but mainly after the 2000s, this basin was a subject to an intensification process of fast‐growing crop areas with soybeans, corn, wheat and barley as the main crops, which generally substituted native grasslands (Hastings et al., 2020). Despite showing a high inter‐annual rainfall variability, most of its area is under rain‐fed crop production.…”

Section: Study Area Proposed Scenarios and Datamentioning

confidence: 99%

“…To show the appropriateness of the approach in tackling the two main issues around water (quantity and quality), and their interaction with the economic activities within the basin, we calibrate and run the model and the scenarios on a particular basin of the temperate region of South America. This basin of the San Salvador River in Uruguay is characterised by the expansion of agriculture along both the extensive and intensive margins, the growth of urban areas and industrial development, and as a result, an increasing pressure on water resources (Hastings et al., 2020; MVOTMA, 2017). The scenarios implemented replicate two of the main challenges in the basin.…”

Section: Introductionmentioning

confidence: 99%

An integrated assessment model of the impacts of agricultural intensification: Trade‐offs between economic benefits and water quality under uncertainty

Souto,

Carriquiry,

Rosas

2024

Aus J Agri & Res Econ

View full text Add to dashboard Cite

We integrate a model that simulates biophysical processes in soils and water with spatial and temporal heterogeneity at the basin scale with an economic model of decisions under uncertainty, to simultaneously evaluate the economic and environmental effects of farming practices and land uses that characterise agricultural intensification. The introduction of uncertainty allows the evaluation of economic impacts both due to changes in average profits and in their volatility. Through our model integration, we endogenously tackle the trade‐offs between economic benefits and environmental outcomes, in terms of nutrient levels in water. Results show that a sizable increase in economic benefits from supplemental irrigation comes from lower risk premiums. Medium‐to‐high increments of fertiliser rates in irrigated crops are dominated in terms of economic benefits by low fertiliser rate increments. We find that water quality deteriorates with intensive farming practices. However, the magnitude of the trade‐offs between economic benefits and water quality is mixed and depends on the nutrient and level of risk aversion considered. The ability of our model to quantify and document the mentioned effects is a relevant input to inform the decision‐making process of agricultural and environmental authorities, often characterised by competing and opposing objectives.

show abstract

“…Uruguay has a humid subtropical climate (Cfa, according to the Köppen climate classification) with a mean temperature in the warmest month equal to 22 • C or higher [18]. The study area is characterized by total annual precipitation that varies between 1000 mm and 1500 mm and a temperature that can vary between 3 • C and 30 • C [19].…”

Section: Dataset Descriptionmentioning

confidence: 99%

Water-Quality Data Imputation with a High Percentage of Missing Values: A Machine Learning Approach

et al. 2021

Self Cite

View full text Add to dashboard Cite

The monitoring of surface-water quality followed by water-quality modeling and analysis are essential for generating effective strategies in surface-water-resource management. However, worldwide, particularly in developing countries, water-quality studies are limited due to the lack of a complete and reliable dataset of surface-water-quality variables. In this context, several statistical and machine-learning models were assessed for imputing water-quality data at six monitoring stations located in the Santa Lucía Chico river (Uruguay), a mixed lotic and lentic river system. The challenge of this study is represented by the high percentage of missing data (between 50% and 70%) and the high temporal and spatial variability that characterizes the water-quality variables. The competing algorithms implement univariate and multivariate imputation methods (inverse distance weighting (IDW), Random Forest Regressor (RFR), Ridge (R), Bayesian Ridge (BR), AdaBoost (AB), Hubber Regressor (HR), Support Vector Regressor (SVR) and K-nearest neighbors Regressor (KNNR)). According to the results, more than 76% of the imputation outcomes are considered “satisfactory” (NSE > 0.45). The imputation performance shows better results at the monitoring stations located inside the reservoir than those positioned along the mainstream. IDW was the model with the best imputation results, followed by RFR, HR and SVR. The approach proposed in this study is expected to aid water-resource researchers and managers in augmenting water-quality datasets and overcoming the missing data issue to increase the number of future studies related to the water-quality matter.

show abstract

Land-Cover Mapping of Agricultural Areas Using Machine Learning in Google Earth Engine

Cited by 7 publications

References 19 publications

Impacts of irrigation development on water quality in the San Salvador watershed (Part 1)

Impacts of irrigation development on water quality in the San Salvador watershed (Part 1)

An integrated assessment model of the impacts of agricultural intensification: Trade‐offs between economic benefits and water quality under uncertainty

Water-Quality Data Imputation with a High Percentage of Missing Values: A Machine Learning Approach

Contact Info

Product

Resources

About