Complete Benchmark Results

Full field-level and subfield-level benchmarks for CV10, LORO, and LOYO across all country-crop combinations.

This page contains the complete benchmark table for YieldSAT. It includes 10-fold cross-validation (CV10), leave-one-region-out (LORO), and leave-one-year-out (LOYO) evaluation for the temporal, spatial-temporal, and multimodal fusion baselines discussed on the main project page.

Experiment Setup	Modalities	Fusion Method	Model	Field-Level	Subfield (Pixel)-Level
CV10	Sentinel-2	X	Transformer^[1]	0.77	1.35	0.73	0.63	0.87	0.78	0.79	0.82	0.75	0.35	0.62	0.49	0.75	0.67	0.56	1.26	0.72	0.56	0.61	2.33	0.62	0.94	0.76	1.17	0.44	2.16	0.38	0.94	0.22	1.39	0.44	1.25	0.32	2.43	0.38	1.24
LSTM^[5]	0.79	1.29	0.72	0.64	0.85	0.84	0.75	0.88	0.68	0.39	0.62	0.49	0.62	0.83	-0.87	2.60	0.66	0.62	0.59	2.40	0.60	0.96	0.74	1.21	0.42	2.20	0.34	0.98	0.22	1.39	0.36	1.33	-0.32	3.38	0.37	1.26
3D-ConvLSTM^[2]	0.84	1.13	0.79	0.55	0.92	0.62	0.82	0.74	0.76	0.34	0.73	0.42	0.81	0.58	0.65	1.12	0.77	0.51	0.65	2.20	0.65	0.90	0.79	1.10	0.45	2.13	0.39	0.94	0.23	1.38	0.49	1.20	0.34	2.40	0.41	1.22
3D-LSTM^[4]	0.74	1.44	0.77	0.58	0.89	0.70	0.82	0.74	0.76	0.34	0.63	0.48	0.82	0.57	0.54	1.28	0.73	0.56	0.59	2.37	0.65	0.90	0.79	1.08	0.46	2.13	0.39	0.93	0.24	1.37	0.48	1.20	0.30	2.46	0.39	1.23
Sentinel-2 + ADM	Input Fusion	Transformer^[1]	0.69	1.55	0.72	0.64	0.83	0.87	0.79	0.81	0.71	0.37	0.61	0.49	0.76	0.65	0.61	1.19	0.73	0.55	0.52	2.57	0.58	0.98	0.70	1.30	0.44	2.17	0.37	0.96	0.22	1.39	0.45	1.24	0.38	2.32	0.39	1.23
LSTM^[5]	0.76	1.39	0.72	0.64	0.85	0.83	0.81	0.78	0.64	0.42	0.58	0.52	0.81	0.58	0.63	1.16	0.72	0.56	0.58	2.41	0.59	0.98	0.75	1.20	0.43	2.18	0.33	0.99	0.21	1.40	0.47	1.21	0.35	2.38	0.39	1.23
3D-ConvLSTM^[2]	0.12	2.63	0.82	0.52	0.89	0.72	0.83	0.72	0.76	0.34	0.72	0.42	0.78	0.63	0.70	1.03	0.80	0.48	0.08	3.58	0.68	0.87	0.78	1.11	0.46	2.12	0.38	0.94	0.23	1.38	0.42	1.27	0.39	2.30	0.42	1.20
3D-LSTM^[4]	0.40	2.17	0.76	0.59	0.87	0.77	0.84	0.71	0.75	0.35	0.72	0.42	0.81	0.59	0.62	1.17	0.77	0.52	0.36	2.97	0.64	0.91	0.78	1.13	0.46	2.12	0.41	0.93	0.24	1.37	0.49	1.20	0.37	2.34	0.40	1.22
Feature Fusion	AFF^[4]	0.84	1.12	0.84	0.49	0.92	0.60	0.84	0.70	0.80	0.31	0.71	0.43	0.80	0.60	0.74	0.96	0.82	0.46	0.70	2.03	0.73	0.79	0.84	0.96	0.46	2.12	0.44	0.90	0.24	1.37	0.49	1.20	0.44	2.20	0.43	1.19
MMGF^[3]	0.79	1.30	0.82	0.51	0.89	0.69	0.76	0.86	0.80	0.31	0.59	0.51	0.75	0.68	0.77	0.90	0.75	0.53	0.65	2.20	0.70	0.84	0.80	1.07	0.42	2.19	0.42	0.92	0.20	1.40	0.44	1.26	0.44	2.21	0.40	1.22
LORO	Sentinel-2	X	Transformer^[1]	0.55	1.88	0.59	0.77	0.71	1.16	0.35	1.43	0.33	0.57	0.37	0.63	0.17	1.22	0.01	1.89	0.63	0.65	0.43	2.80	0.52	1.05	0.61	1.49	0.27	2.47	0.21	1.07	0.11	1.48	0.09	1.59	0.10	2.79	0.31	1.31
LSTM^[5]	0.47	2.05	0.64	0.72	0.70	1.18	0.39	1.39	0.28	0.59	0.27	0.68	-0.16	1.45	-2.71	3.66	0.63	0.65	0.44	2.79	0.55	1.03	0.61	1.48	0.27	2.46	0.16	1.10	0.11	1.48	-0.05	1.71	-0.78	3.93	0.34	1.28
3D-ConvLSTM^[2]	0.68	1.59	0.69	0.67	0.80	0.95	0.55	1.19	0.37	0.55	0.47	0.58	0.25	1.16	0.14	1.76	0.68	0.61	0.54	2.52	0.57	1.01	0.69	1.33	0.33	2.35	0.19	1.08	0.16	1.44	0.12	1.57	0.07	2.84	0.36	1.26
3D-LSTM^[4]	0.49	2.00	0.70	0.67	0.81	0.92	0.59	1.13	0.41	0.53	0.48	0.57	0.26	1.16	-0.08	1.98	0.65	0.63	0.39	2.91	0.59	0.98	0.71	1.30	0.34	2.33	0.22	1.06	0.20	1.41	0.17	1.52	0.02	2.92	0.36	1.26
Sentinel-2 + ADM	Input Fusion	Transformer^[1]	0.44	2.10	0.67	0.70	0.63	1.30	0.52	1.22	0.20	0.62	0.36	0.64	0.18	1.22	-0.34	2.20	0.59	0.68	0.38	2.93	0.53	1.04	0.53	1.63	0.31	2.39	0.15	1.11	0.12	1.47	0.13	1.56	-0.02	2.97	0.30	1.31
LSTM^[5]	0.43	2.12	0.66	0.71	0.61	1.34	0.38	1.39	0.29	0.58	0.26	0.69	0.20	1.20	-1.39	2.94	0.56	0.71	0.48	2.69	0.54	1.03	0.53	1.64	0.28	2.45	0.12	1.13	0.11	1.48	0.05	1.63	-0.36	3.44	0.32	1.30
3D-ConvLSTM^[2]	0.33	2.30	0.73	0.63	0.81	0.93	0.62	1.09	0.51	0.48	0.49	0.57	0.23	1.18	0.12	1.78	0.60	0.67	0.21	3.31	0.60	0.97	0.70	1.32	0.34	2.34	0.26	1.04	0.17	1.43	0.07	1.61	0.10	2.79	0.33	1.29
3D-LSTM^[4]	0.23	2.46	0.66	0.70	0.74	1.09	0.65	1.05	0.47	0.50	0.48	0.58	0.03	1.32	-0.16	2.05	0.62	0.66	0.39	2.90	0.57	1.00	0.64	1.44	0.37	2.29	0.26	1.04	0.17	1.43	0.03	1.64	-0.02	2.97	0.35	1.27
Feature Fusion	AFF^[4]	0.53	1.92	0.78	0.57	0.87	0.78	0.55	1.19	0.63	0.42	0.52	0.55	0.07	1.29	-1.85	3.21	0.60	0.68	0.49	2.64	0.65	0.90	0.78	1.12	0.34	2.35	0.35	0.97	0.18	1.42	0.15	1.55	-0.58	3.70	0.34	1.28
MMGF^[3]	0.59	1.80	0.65	0.71	0.78	1.00	0.10	1.68	0.30	0.58	0.23	0.70	-0.56	1.68	-0.95	2.65	0.54	0.73	0.50	2.63	0.54	1.04	0.68	1.35	0.13	2.69	0.20	1.07	0.07	1.51	-0.13	1.77	-0.34	3.41	0.31	1.31
LOYO	Sentinel-2	X	Transformer^[1]	0.57	1.83	0.52	0.84	0.78	0.99	0.19	1.59	0.28	0.59	-0.09	0.83	0.33	1.10	0.14	1.76	0.60	0.68	0.42	2.83	0.48	1.10	0.67	1.38	0.19	2.60	0.16	1.10	0.05	1.53	0.14	1.55	0.13	2.74	0.33	1.29
LSTM^[5]	0.46	2.06	0.50	0.85	0.77	1.02	0.19	1.59	0.06	0.67	-0.05	0.82	-0.07	1.39	-1.74	3.14	0.61	0.67	0.39	2.90	0.46	1.12	0.61	1.49	0.15	2.66	0.04	1.18	0.08	1.50	-0.05	1.71	-0.68	3.82	0.33	1.29
3D-ConvLSTM^[2]	0.61	1.75	0.65	0.71	0.78	1.00	0.20	1.58	0.36	0.55	-0.06	0.82	0.43	1.02	0.23	1.67	0.63	0.65	0.48	2.68	0.54	1.04	0.67	1.38	0.15	2.67	0.19	1.08	0.06	1.52	0.21	1.49	0.15	2.71	0.34	1.28
3D-LSTM^[4]	0.53	1.93	0.66	0.70	0.77	1.02	0.36	1.42	0.12	0.65	-0.33	0.92	0.41	1.03	0.00	1.90	0.62	0.66	0.47	2.70	0.55	1.03	0.68	1.35	0.21	2.56	0.13	1.12	0.03	1.54	0.18	1.52	0.01	2.93	0.35	1.27
Sentinel-2 + ADM	Input Fusion	Transformer^[1]	0.33	2.30	0.65	0.72	0.75	1.08	0.25	1.54	-0.09	0.72	0.11	0.75	0.47	0.98	0.02	1.88	0.56	0.71	0.24	3.24	0.49	1.09	0.60	1.51	0.22	2.54	0.08	1.15	0.11	1.48	0.25	1.45	0.06	2.86	0.30	1.32
LSTM^[5]	0.42	2.13	0.62	0.74	0.74	1.08	0.29	1.49	0.26	0.59	0.12	0.75	0.58	0.87	0.33	1.56	0.54	0.73	0.44	2.78	0.49	1.09	0.61	1.49	0.19	2.60	0.17	1.09	0.09	1.50	0.31	1.38	0.18	2.67	0.30	1.32
3D-ConvLSTM^[2]	-0.01	2.82	0.67	0.69	0.77	1.03	0.45	1.32	0.34	0.56	-0.15	0.86	0.49	0.96	0.46	1.39	0.56	0.71	-0.02	3.75	0.56	1.01	0.64	1.43	0.27	2.47	0.19	1.08	0.04	1.54	0.22	1.47	0.22	2.60	0.31	1.31
3D-LSTM^[4]	0.18	2.54	0.62	0.74	0.78	0.99	0.28	1.50	0.45	0.52	-0.07	0.82	0.26	1.15	0.15	1.75	0.52	0.74	0.25	3.23	0.53	1.05	0.68	1.34	0.22	2.55	0.22	1.06	0.06	1.52	0.13	1.56	0.15	2.72	0.30	1.32
Feature Fusion	AFF^[4]	0.33	2.30	0.77	0.59	0.81	0.93	0.42	1.35	0.38	0.54	0.14	0.74	0.44	1.00	0.19	1.71	0.53	0.73	0.35	2.99	0.66	0.89	0.72	1.27	0.29	2.43	0.29	1.02	0.11	1.48	0.25	1.45	0.16	2.70	0.32	1.30
MMGF^[3]	0.31	2.33	0.66	0.70	0.36	1.71	0.39	1.38	0.38	0.55	-0.08	0.83	0.15	1.24	-0.03	1.92	0.48	0.77	0.30	3.10	0.57	1.00	0.28	2.03	0.23	2.53	0.24	1.05	0.06	1.52	0.05	1.63	0.06	2.86	0.28	1.34

Experiment Setup

Modalities

Fusion Method

Model

Field-Level

Subfield (Pixel)-Level

ARG-C

ARG-S

ARG-W

BRA-C

BRA-S

BRA-W

GER-R

GER-W

URG-S

ARG-C

ARG-S

ARG-W

BRA-C

BRA-S

BRA-W

GER-R

GER-W

URG-S

RMSE

CV10

Sentinel-2

Transformer^[1]

0.77

1.35

0.73

0.63

0.87

0.78

0.79

0.82

0.75

0.35

0.62

0.49

0.75

0.67

0.56

1.26

0.72

0.56

0.61

2.33

0.62

0.94

0.76

1.17

0.44

2.16

0.38

0.94

0.22

1.39

0.44

1.25

0.32

2.43

0.38

1.24

LSTM^[5]

0.79

1.29

0.72

0.64

0.85

0.84

0.75

0.88

0.68

0.39

0.62

0.49

0.62

0.83

-0.87

2.60

0.66

0.62

0.59

2.40

0.60

0.96

0.74

1.21

0.42

2.20

0.34

0.98

0.22

1.39

0.36

1.33

-0.32

3.38

0.37

1.26

3D-ConvLSTM^[2]

0.84

1.13

0.79

0.55

0.92

0.62

0.82

0.74

0.76

0.34

0.73

0.42

0.81

0.58

0.65

1.12

0.77

0.51

0.65

2.20

0.65

0.90

0.79

1.10

0.45

2.13

0.39

0.94

0.23

1.38

0.49

1.20

0.34

2.40

0.41

1.22

3D-LSTM^[4]

0.74

1.44

0.77

0.58

0.89

0.70

0.82

0.74

0.76

0.34

0.63

0.48

0.82

0.57

0.54

1.28

0.73

0.56

0.59

2.37

0.65

0.90

0.79

1.08

0.46

2.13

0.39

0.93

0.24

1.37

0.48

1.20

0.30

2.46

0.39

1.23

Sentinel-2 + ADM

Input Fusion

Transformer^[1]

0.69

1.55

0.72

0.64

0.83

0.87

0.79

0.81

0.71

0.37

0.61

0.49

0.76

0.65

0.61

1.19

0.73

0.55

0.52

2.57

0.58

0.98

0.70

1.30

0.44

2.17

0.37

0.96

0.22

1.39

0.45

1.24

0.38

2.32

0.39

1.23

LSTM^[5]

0.76

1.39

0.72

0.64

0.85

0.83

0.81

0.78

0.64

0.42

0.58

0.52

0.81

0.58

0.63

1.16

0.72

0.56

0.58

2.41

0.59

0.98

0.75

1.20

0.43

2.18

0.33

0.99

0.21

1.40

0.47

1.21

0.35

2.38

0.39

1.23

3D-ConvLSTM^[2]

0.12

2.63

0.82

0.52

0.89

0.72

0.83

0.72

0.76

0.34

0.72

0.42

0.78

0.63

0.70

1.03

0.80

0.48

0.08

3.58

0.68

0.87

0.78

1.11

0.46

2.12

0.38

0.94

0.23

1.38

0.42

1.27

0.39

2.30

0.42

1.20

3D-LSTM^[4]

0.40

2.17

0.76

0.59

0.87

0.77

0.84

0.71

0.75

0.35

0.72

0.42

0.81

0.59

0.62

1.17

0.77

0.52

0.36

2.97

0.64

0.91

0.78

1.13

0.46

2.12

0.41

0.93

0.24

1.37

0.49

1.20

0.37

2.34

0.40

1.22

Feature Fusion

AFF^[4]

0.84

1.12

0.84

0.49

0.92

0.60

0.84

0.70

0.80

0.31

0.71

0.43

0.80

0.60

0.74

0.96

0.82

0.46

0.70

2.03

0.73

0.79

0.84

0.96

0.46

2.12

0.44

0.90

0.24

1.37

0.49

1.20

0.44

2.20

0.43

1.19

MMGF^[3]

0.79

1.30

0.82

0.51

0.89

0.69

0.76

0.86

0.80

0.31

0.59

0.51

0.75

0.68

0.77

0.90

0.75

0.53

0.65

2.20

0.70

0.84

0.80

1.07

0.42

2.19

0.42

0.92

0.20

1.40

0.44

1.26

0.44

2.21

0.40

1.22

LORO

Sentinel-2

Transformer^[1]

0.55

1.88

0.59

0.77

0.71

1.16

0.35

1.43

0.33

0.57

0.37

0.63

0.17

1.22

0.01

1.89

0.63

0.65

0.43

2.80

0.52

1.05

0.61

1.49

0.27

2.47

0.21

1.07

0.11

1.48

0.09

1.59

0.10

2.79

0.31

1.31

LSTM^[5]

0.47

2.05

0.64

0.72

0.70

1.18

0.39

1.39

0.28

0.59

0.27

0.68

-0.16

1.45

-2.71

3.66

0.63

0.65

0.44

2.79

0.55

1.03

0.61

1.48

0.27

2.46

0.16

1.10

0.11

1.48

-0.05

1.71

-0.78

3.93

0.34

1.28

3D-ConvLSTM^[2]

0.68

1.59

0.69

0.67

0.80

0.95

0.55

1.19

0.37

0.55

0.47

0.58

0.25

1.16

0.14

1.76

0.68

0.61

0.54

2.52

0.57

1.01

0.69

1.33

0.33

2.35

0.19

1.08

0.16

1.44

0.12

1.57

0.07

2.84

0.36

1.26

3D-LSTM^[4]

0.49

2.00

0.70

0.67

0.81

0.92

0.59

1.13

0.41

0.53

0.48

0.57

0.26

1.16

-0.08

1.98

0.65

0.63

0.39

2.91

0.59

0.98

0.71

1.30

0.34

2.33

0.22

1.06

0.20

1.41

0.17

1.52

0.02

2.92

0.36

1.26

Sentinel-2 + ADM

Input Fusion

Transformer^[1]

0.44

2.10

0.67

0.70

0.63

1.30

0.52

1.22

0.20

0.62

0.36

0.64

0.18

1.22

-0.34

2.20

0.59

0.68

0.38

2.93

0.53

1.04

0.53

1.63

0.31

2.39

0.15

1.11

0.12

1.47

0.13

1.56

-0.02

2.97

0.30

1.31

LSTM^[5]

0.43

2.12

0.66

0.71

0.61

1.34

0.38

1.39

0.29

0.58

0.26

0.69

0.20

1.20

-1.39

2.94

0.56

0.71

0.48

2.69

0.54

1.03

0.53

1.64

0.28

2.45

0.12

1.13

0.11

1.48

0.05

1.63

-0.36

3.44

0.32

1.30

3D-ConvLSTM^[2]

0.33

2.30

0.73

0.63

0.81

0.93

0.62

1.09

0.51

0.48

0.49

0.57

0.23

1.18

0.12

1.78

0.60

0.67

0.21

3.31

0.60

0.97

0.70

1.32

0.34

2.34

0.26

1.04

0.17

1.43

0.07

1.61

0.10

2.79

0.33

1.29

3D-LSTM^[4]

0.23

2.46

0.66

0.70

0.74

1.09

0.65

1.05

0.47

0.50

0.48

0.58

0.03

1.32

-0.16

2.05

0.62

0.66

0.39

2.90

0.57

1.00

0.64

1.44

0.37

2.29

0.26

1.04

0.17

1.43

0.03

1.64

-0.02

2.97

0.35

1.27

Feature Fusion

AFF^[4]

0.53

1.92

0.78

0.57

0.87

0.78

0.55

1.19

0.63

0.42

0.52

0.55

0.07

1.29

-1.85

3.21

0.60

0.68

0.49

2.64

0.65

0.90

0.78

1.12

0.34

2.35

0.35

0.97

0.18

1.42

0.15

1.55

-0.58

3.70

0.34

1.28

MMGF^[3]

0.59

1.80

0.65

0.71

0.78

1.00

0.10

1.68

0.30

0.58

0.23

0.70

-0.56

1.68

-0.95

2.65

0.54

0.73

0.50

2.63

0.54

1.04

0.68

1.35

0.13

2.69

0.20

1.07

0.07

1.51

-0.13

1.77

-0.34

3.41

0.31

1.31

LOYO

Sentinel-2

Transformer^[1]

0.57

1.83

0.52

0.84

0.78

0.99

0.19

1.59

0.28

0.59

-0.09

0.83

0.33

1.10

0.14

1.76

0.60

0.68

0.42

2.83

0.48

1.10

0.67

1.38

0.19

2.60

0.16

1.10

0.05

1.53

0.14

1.55

0.13

2.74

0.33

1.29

LSTM^[5]

0.46

2.06

0.50

0.85

0.77

1.02

0.19

1.59

0.06

0.67

-0.05

0.82

-0.07

1.39

-1.74

3.14

0.61

0.67

0.39

2.90

0.46

1.12

0.61

1.49

0.15

2.66

0.04

1.18

0.08

1.50

-0.05

1.71

-0.68

3.82

0.33

1.29

3D-ConvLSTM^[2]

0.61

1.75

0.65

0.71

0.78

1.00

0.20

1.58

0.36

0.55

-0.06

0.82

0.43

1.02

0.23

1.67

0.63

0.65

0.48

2.68

0.54

1.04

0.67

1.38

0.15

2.67

0.19

1.08

0.06

1.52

0.21

1.49

0.15

2.71

0.34

1.28

3D-LSTM^[4]

0.53

1.93

0.66

0.70

0.77

1.02

0.36

1.42

0.12

0.65

-0.33

0.92

0.41

1.03

0.00

1.90

0.62

0.66

0.47

2.70

0.55

1.03

0.68

1.35

0.21

2.56

0.13

1.12

0.03

1.54

0.18

1.52

0.01

2.93

0.35

1.27

Sentinel-2 + ADM

Input Fusion

Transformer^[1]

0.33

2.30

0.65

0.72

0.75

1.08

0.25

1.54

-0.09

0.72

0.11

0.75

0.47

0.98

0.02

1.88

0.56

0.71

0.24

3.24

0.49

1.09

0.60

1.51

0.22

2.54

0.08

1.15

0.11

1.48

0.25

1.45

0.06

2.86

0.30

1.32

LSTM^[5]

0.42

2.13

0.62

0.74

1.08

0.29

1.49

0.26

0.59

0.12

0.75

0.58

0.87

0.33

1.56

0.54

0.73

0.44

2.78

0.49

1.09

0.61

1.49

0.19

2.60

0.17

1.09

0.09

1.50

0.31

1.38

0.18

2.67

0.30

1.32

3D-ConvLSTM^[2]

-0.01

2.82

0.67

0.69

0.77

1.03

0.45

1.32

0.34

0.56

-0.15

0.86

0.49

0.96

0.46

1.39

0.56

0.71

-0.02

3.75

0.56

1.01

0.64

1.43

0.27

2.47

0.19

1.08

0.04

1.54

0.22

1.47

0.22

2.60

0.31

1.31

3D-LSTM^[4]

0.18

2.54

0.62

0.74

0.78

0.99

0.28

1.50

0.45

0.52

-0.07

0.82

0.26

1.15

0.15

1.75

0.52

0.74

0.25

3.23

0.53

1.05

0.68

1.34

0.22

2.55

0.22

1.06

0.06

1.52

0.13

1.56

0.15

2.72

0.30

1.32

Feature Fusion

AFF^[4]

0.33

2.30

0.77

0.59

0.81

0.93

0.42

1.35

0.38

0.54

0.14

0.74

0.44

1.00

0.19

1.71

0.53

0.73

0.35

2.99

0.66

0.89

0.72

1.27

0.29

2.43

0.29

1.02

0.11

1.48

0.25

1.45

0.16

2.70

0.32

1.30

MMGF^[3]

0.31

2.33

0.66

0.70

0.36

1.71

0.39

1.38

0.38

0.55

-0.08

0.83

0.15

1.24

-0.03

1.92

0.48

0.77

0.30

3.10

0.57

1.00

0.28

2.03

0.23

2.53

0.24

1.05

0.06

1.52

0.05

1.63

0.06

2.86

0.28

1.34

ARG-C: Argentina Corn, ARG-S: Argentina Soybean, ARG-W: Argentina Wheat, BRA-C: Brazil Corn, BRA-S: Brazil Soybean, BRA-W: Brazil Wheat, GER-R: Germany Rapeseed, GER-W: Germany Wheat, URG-S: Uruguay Soybean. Blank or X indicates no fusion method is used for Sentinel-2-only models in the corresponding setup. Under Experiment Setup, CV10 refers to 10-fold cross-validation, LORO refers to Leave-One-Region-Out, and LOYO refers to Leave-One-Year-Out. Superscript references next to model names link to the benchmark papers listed below.

Benchmark References

[1] P. Helber et al., “Crop yield prediction: An operational approach to crop yield modeling on field and subfield level with machine learning models,” in IGARSS - IEEE international geoscience and remote sensing symposium, IEEE, 2023, pp. 2763–2766.

[2] P. Helber, B. Bischke, C. Packbier, P. Habelitz, and F. Seefeldt, “An operational approach to large-scale crop yield prediction with spatio-temporal machine learning models,” in IGARSS 2024-2024 IEEE international geoscience and remote sensing symposium, IEEE, 2024, pp. 4299–4302.

[3] F. Mena et al., “Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction,” Remote Sensing of Environment, vol. 318, p. 114547, 2025.

[4] M. Miranda, D. Pathak, M. Nuske, and A. Dengel, “Multi-modal fusion methods with local neighborhood information for crop yield prediction at field and subfield levels,” in IGARSS 2024-2024 IEEE international geoscience and remote sensing symposium, IEEE, 2024, pp. 4307–4311.

[5] D. Pathak et al., “Predicting crop yield with machine learning: An extensive analysis of input modalities and models on a field and sub-field level,” in IGARSS- IEEE international geoscience and remote sensing symposium, 2023, pp. 2767–2770. doi: 10.1109/IGARSS52108.2023.10282318.